© 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

    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

    PrevNext
    Close
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing bracket or parenthesis (negative activations)

    python-code · gemini-2.5-flash-lite

    subtraction operator

    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
     &
    -0.03
     |
    -0.03
    args
    -0.02
    ?
    -0.02
    [str
    -0.01
    .is
    -0.01
     dist
    -0.01
     distances
    -0.01
    _string
    -0.01
     has
    -0.01
    Positive Logits
    ")
    0.04
    )
    0.04
    ')
    0.03
    ])
    0.03
    ())
    0.03
    oal
    0.03
    join
    0.03
    stination
    0.02
    arget
    0.02
    ).
    0.02
    Activations Density 92.021%

    No Known Activations