© 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

    print statement or return value (negative activations)

    python-code · gemini-2.5-flash-lite

    sqlite3 connection assignment

    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
     :
    -0.04
     found
    -0.03
    over
    -0.02
    :
    -0.02
    <extra_output_id:2047>
    -0.01
    _move
    -0.01
     ↵
    -0.01
     e
    -0.01
    ow
    -0.01
     for
    -0.00
    Positive Logits
     it
    0.08
     each
    0.02
    _data
    0.01
    rack
    0.01
    _input
    0.01
    .b
    0.01
    .in
    0.01
     initial
    0.01
     data
    0.01
    data
    0.00
    Activations Density 98.895%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    itertools.permutations call

    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
    rt
    -0.04
    join
    -0.03
    lable
    -0.02
     as
    -0.02
     total
    -0.01
     rows
    -0.01
     number
    -0.01
     self
    -0.01
    _dict
    -0.01
     None
    -0.00
    Positive Logits
    m
    0.07
    inal
    0.06
    mit
    0.06
    rite
    0.06
    ge
    0.05
    ip
    0.05
    ine
    0.04
     product
    0.03
     the
    0.03
    ain
    0.03
    Activations Density 67.020%

    No Known Activations