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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 2615
    Prev
    Next
    INDEX
    Explanations

    the term "__init__", which is often used as a Python constructor

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jstor
    -0.69
    ьаж
    -0.63
     corti
    -0.61
     DOI
    -0.60
    DOI
    -0.59
     morrow
    -0.59
    DJANGO
    -0.59
     Formation
    -0.58
    EndGlobalSection
    -0.58
     formation
    -0.57
    POSITIVE LOGITS
    init
    2.88
     init
    2.58
    Init
    2.03
     Init
    1.96
    INIT
    1.94
     INIT
    1.70
     initialization
    1.58
    初始化
    1.47
     初始化
    1.43
     Initialization
    1.39
    Activations Density 0.011%

    No Known Activations