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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74345
    Prev
    Next
    INDEX
    Explanations

    Possible start of article title

    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
    AndEndTag
    -0.73
     nahilalakip
    -0.71
     Италијани
    -0.70
    bootstrapcdn
    -0.69
    EDEFAULT
    -0.68
    basicConfig
    -0.66
     noires
    -0.65
    exitRule
    -0.64
    WireFormatLite
    -0.64
    afficheront
    -0.63
    POSITIVE LOGITS
    labelledby
    0.48
    ysaccharide
    0.46
    Géographie
    0.46
    owią
    0.44
    )];
    
    0.43
    addis
    0.43
    icorn
    0.43
    siella
    0.42
    служи
    0.42
    queous
    0.41
    Activations Density 0.002%

    No Known Activations