© 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

    is alpha

    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
    ig
    -0.04
     This
    -0.03
    ep
    -0.02
    value
    -0.02
    P
    -0.01
    able
    -0.01
    .de
    -0.01
     P
    -0.01
     t
    -0.01
    _size
    -0.01
    Positive Logits
    N
    0.09
    ħ
    0.08
    _n
    0.08
    120
    0.07
    Ĩ
    0.06
    _number
    0.05
    ns
    0.05
    lause
    0.05
    _num
    0.05
    ilen
    0.05
    Activations Density 14.742%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    combinations_with_replacement

    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
    .heapp
    -0.08
    @
    -0.08
    <
    -0.06
    ["
    -0.06
    ['
    -0.06
    [y
    -0.06
    .remove
    -0.06
    [neighbor
    -0.05
    .pop
    -0.05
    .keys
    -0.05
    Positive Logits
    lit
    0.09
    lause
    0.09
    lauses
    0.07
    ((
    0.07
     form
    0.05
     [[
    0.05
    _li
    0.05
    form
    0.05
    ([
    0.05
     ((
    0.05
    Activations Density 34.789%

    No Known Activations