Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31144
    Prev
    Next
    INDEX
    Explanations

    mentions of being sure about something or checking if something is true

    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
     demurrer
    -0.60
    jstor
    -0.56
     degeneracy
    -0.55
     tenn
    -0.54
     Shops
    -0.54
     degenerate
    -0.53
     Peng
    -0.52
    kegaard
    -0.50
    anum
    -0.50
    힘
    -0.50
    POSITIVE LOGITS
    PerformLayout
    0.71
    Архівовано
    0.68
    dafx
    0.65
     juiste
    0.65
    verwijspagina
    0.63
    انتهای
    0.63
     cohé
    0.61
    pidou
    0.61
    correct
    0.60
    devamını
    0.59
    Activations Density 0.109%

    No Known Activations