© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    Side-by-side compare needs a wider screen.
    Open other featureClose compare
    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment or parameter passing (negative activations)

    python-code · gemini-2.5-flash-lite

    return statement after function definition

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     found
    -0.05
    type
    -0.04
     while
    -0.04
    ((
    -0.03
     tuple
    -0.03
     Tuple
    -0.03
    alc
    -0.03
    .name
    -0.03
    .id
    -0.03
    over
    -0.03
    Positive Logits
    +
    0.02
     graph
    0.02
    _data
    0.02
     grid
    0.01
    _input
    0.01
    (con
    0.01
    ilename
    0.01
    (st
    0.01
    _file
    0.01
    or
    0.01
    Activations Density 69.237%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string formatting specifier (negative activations)

    python-code · gemini-2.5-flash-lite

    variable name 'e' follows '★'

    python-code · gemini-2.5-flash-lite
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    self
    -0.03
     self
    -0.03
    ?
    -0.02
     it
    -0.01
    (self
    -0.01
     "
    -0.01
     print
    -0.01
     [
    -0.01
    act
    -0.01
     best
    -0.00
    Positive Logits
    sed
    0.02
    ized
    0.02
    ble
    0.02
    ated
    0.02
    cted
    0.02
    ted
    0.02
    args
    0.02
    ied
    0.02
    sible
    0.02
    vailable
    0.02
    Activations Density 50.762%

    No Known Activations