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. 9-RES-MATRYOSHKA-DC
    4. 16597
    Prev
    Next
    INDEX
    Explanations

    the word "facial".

    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
     שוליים
    -0.93
    PreExecute
    -0.80
    Linki
    -0.78
     Kessel
    -0.76
    สือ
    -0.76
    sidemargin
    -0.75
     مشين
    -0.75
    ագրություններ
    -0.75
     financieras
    -0.73
    iguity
    -0.71
    POSITIVE LOGITS
     facial
    1.05
    Facial
    0.94
    facial
    0.93
     Facial
    0.90
     fibrillation
    0.71
     Schre
    0.70
    ="&#
    0.69
    óch
    0.66
    pthread
    0.64
     fac
    0.64
    Activations Density 0.002%

    No Known Activations