© 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. 20-CLT-HP
    7. 74587
    Prev
    Next
    INDEX
    Explanations

    site/sight

    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
    Tikang
    -0.69
    OGND
    -0.68
     ***!
    -0.66
    sizeCache
    -0.62
     تضيفلها
    -0.61
    पया
    -0.60
     Himself
    -0.59
     surla
    -0.59
    ượng
    -0.57
     LoggerFactory
    -0.57
    POSITIVE LOGITS
     sights
    1.19
     sites
    1.02
    sights
    0.94
     site
    0.83
     cross
    0.79
     sight
    0.78
     Sites
    0.77
    Sites
    0.68
     Site
    0.67
    sites
    0.67
    Activations Density 0.000%

    No Known Activations