© 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. 2-RES-MATRYOSHKA-DC
    7. 3783
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wear" in context

    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
    goose
    -0.55
    пери
    -0.54
     purse
    -0.52
     Fur
    -0.52
     Goose
    -0.52
     يتيمه
    -0.49
     fur
    -0.48
    Goose
    -0.48
     connexes
    -0.47
    olski
    -0.47
    POSITIVE LOGITS
     wear
    3.30
     Wear
    3.03
     wears
    2.86
    Wear
    2.81
     WEAR
    2.81
     wore
    2.73
    wear
    2.63
     wearing
    2.58
     worn
    2.56
     Wearing
    2.50
    Activations Density 0.014%

    No Known Activations