© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 1707
    Prev
    Next
    INDEX
    Explanations

    self attribute access and object methods (negative activations)

    python-code · gemini-2.5-flash-lite

    `__init__` method arguments

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    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
    Not in Any Lists

    No Comments

    Negative Logits
    Î
    -0.23
    (matrix
    -0.17
    Ï
    -0.17
     matrix
    -0.13
    (maze
    -0.11
    _matrix
    -0.10
    atrix
    -0.09
    atri
    -0.08
     maze
    -0.07
    m
    -0.02
    POSITIVE LOGITS
    (grid
    0.21
    grid
    0.18
     grid
    0.18
    rid
    0.18
    _grid
    0.15
    .grid
    0.11
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    Activations Density 100.000%

    No Known Activations