© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1045
    Prev
    Next
    INDEX
    Explanations

    arrogance

    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
     HasFactory
    -1.04
     arrogance
    -0.95
     Мексичка
    -0.91
     complacency
    -0.91
    
    -0.91
     sarcasm
    -0.90
     apathy
    -0.90
     metaphors
    -0.88
    FOOTNOTES
    -0.88
     disambiguazione
    -0.87
    POSITIVE LOGITS
     and
    0.78
    .
    0.63
    ,
    0.63
     in
    0.59
     on
    0.52
     or
    0.50
    ly
    0.49
     of
    0.47
     (
    0.47
    ↵↵
    0.47
    Activations Density 0.048%

    No Known Activations