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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74164
    Prev
    Next
    INDEX
    Explanations

    Arbitrary sentences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CanadaChoose
    -0.63
    Étymologie
    -0.57
    rogly
    -0.54
    Aiheesta
    -0.53
     HasFactory
    -0.52
    مصادر
    -0.52
    EDEFAULT
    -0.52
    #
    -0.51
    ViewById
    -0.50
     nahilalakip
    -0.49
    POSITIVE LOGITS
    Wit
    0.61
     Wit
    0.60
    tableFuture
    0.53
     Brant
    0.52
    litt
    0.52
    urtles
    0.49
    AccessorTable
    0.47
     باخ
    0.47
     Quint
    0.47
    WIT
    0.47
    Activations Density 0.002%

    No Known Activations