© 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. 1898
    Prev
    Next
    INDEX
    Explanations

    `self.y` attribute or `year` attribute (negative activations)

    python-code · gemini-2.5-flash-lite

    closing parenthesis or quote

    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
     {
    -0.10
     (
    -0.06
    =
    -0.06
    ',↵
    -0.05
     [
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    POSITIVE LOGITS
     ("
    0.19
     ('
    0.18
    ("
    0.17
    \n
    0.17
    ('
    0.16
    ="
    0.13
    ='
    0.13
     ↵
    0.05
     <=
    0.05
    '
    0.00
    Activations Density 99.882%

    No Known Activations