© 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. 10917
    Prev
    Next
    INDEX
    Explanations

    a repeated mention of a specific individual or object's crucial element or core attribute

    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
    pieces
    -1.36
    Pieces
    -1.19
     Pieces
    -1.16
     pieces
    -0.97
     <<<<<<<<<<<<<<
    -0.72
    CPtr
    -0.65
     piezas
    -0.63
     pièces
    -0.59
     Pièces
    -0.57
    estal
    -0.57
    POSITIVE LOGITS
     piece
    1.16
    ContentAsync
    0.66
    CloseOperation
    0.63
     tract
    0.60
    Citiți
    0.56
     összefoglaló
    0.56
    liferay
    0.54
    )");
    0.53
    ----+
    0.53
     peace
    0.53
    Activations Density 0.003%

    No Known Activations