© 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

    assignment with keywords

    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
    _line
    -0.03
    city
    -0.03
    _lines
    -0.03
    (line
    -0.02
    line
    -0.02
     line
    -0.02
    lines
    -0.02
     lines
    -0.02
     ((
    -0.02
    ((
    -0.02
    Positive Logits
     for
    0.06
    for
    0.06
     []↵↵
    0.04
    lambda
    0.04
     []↵
    0.04
    %
    0.04
     enumerate
    0.04
     {}↵↵
    0.03
     deque
    0.03
     ['
    0.03
    Activations Density 57.779%

    No Known Activations

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `else` condition keyword (negative activations)

    python-code · gemini-2.5-flash-lite

    json.dumps calls

    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
    join
    -0.04
    lable
    -0.03
     and
    -0.02
    <extra_output_id:2047>
    -0.02
     q
    -0.02
    q
    -0.01
     &
    -0.01
    [(
    -0.01
    gs
    -0.01
     r
    -0.01
    Positive Logits
     {}↵↵
    0.02
    _to
    0.02
     {}↵
    0.02
    _from
    0.01
     to
    0.01
    ffe
    0.01
     from
    0.01
     []↵↵
    0.01
    rom
    0.01
    ob
    0.01
    Activations Density 69.713%

    No Known Activations