© 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. 0-RES-MATRYOSHKA-DC
    7. 12140
    Prev
    Next
    INDEX
    Explanations

    references to object-oriented programming constructs and class definitions, particularly classes, methods, and access modifiers

    oai_token-act-pair · gpt-4.1-nano
    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
    zef
    -0.58
    avares
    -0.52
    HomeAsUpEnabled
    -0.50
    рыя
    -0.50
    hetics
    -0.50
    Jegyzetek
    -0.49
     me
    -0.49
    uire
    -0.49
    Memorials
    -0.47
     get
    -0.46
    POSITIVE LOGITS
    encodeWith
    0.80
    OGND
    0.78
     polys
    0.78
    Personendaten
    0.77
    TProtocol
    0.77
    ::::::::
    0.75
    دانشنامهٔ
    0.74
     doInBackground
    0.72
    AddTagHelper
    0.70
    DockStyle
    0.68
    Activations Density 0.074%

    No Known Activations