© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45090
    Prev
    Next
    INDEX
    Explanations

    illegally

    np_max-act · 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
    rines
    -0.66
     illegally
    -0.60
    ؤلاء
    -0.57
     placebo
    -0.56
    jspx
    -0.55
     constructs
    -0.54
    httphttps
    -0.53
     sumpay
    -0.52
     eset
    -0.49
     holy
    -0.48
    POSITIVE LOGITS
     متعلقه
    0.80
     lenker
    0.71
     OBITUARY
    0.67
    ագրություններ
    0.64
     насељу
    0.63
     demografica
    0.60
    intios
    0.58
    Билгалдахарш
    0.57
    argout
    0.57
    MigrationBuilder
    0.56
    Activations Density 0.153%

    No Known Activations