© 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. 91186
    Prev
    Next
    INDEX
    Explanations

    source

    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
    Source
    -1.28
    source
    -0.95
     Source
    -0.94
     source
    -0.89
    sources
    -0.88
    Sources
    -0.83
     sources
    -0.82
    Билгалдахарш
    -0.80
     Sources
    -0.76
    Begriffsklä
    -0.75
    POSITIVE LOGITS
    hadiran
    0.61
    GEBURTSDATUM
    0.58
    ++)
    
    0.53
    UpInside
    0.52
    __).
    0.50
    hilangan
    0.48
     publiques
    0.46
    ++];
    0.46
    ++){
    
    0.46
     refusé
    0.46
    Activations Density 0.328%

    No Known Activations