© 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. 10980
    Prev
    Next
    INDEX
    Explanations

    references to peeling or removal of the outer layer of something

    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
    LLocation
    -0.63
    ContentAlignment
    -0.60
    UIControlState
    -0.57
     BoxFit
    -0.56
    ímite
    -0.55
    Shotgun
    -0.54
    rouvez
    -0.54
    etzal
    -0.54
    ,:);
    -0.53
    letes
    -0.53
    POSITIVE LOGITS
     peel
    3.77
     Peel
    2.80
     peels
    2.80
    Peel
    2.72
    peel
    2.70
     peeling
    2.61
     peeled
    2.58
     peal
    1.10
    剥
    0.91
    剝
    0.77
    Activations Density 0.000%

    No Known Activations