© 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. 91077
    Prev
    Next
    INDEX
    Explanations

    contests and competitions

    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
     skater
    -0.82
    comfort
    -0.80
     ***!
    -0.79
     Dance
    -0.77
     Мексичка
    -0.73
     dance
    -0.73
     danced
    -0.72
     Skating
    -0.72
     skaters
    -0.71
     Teachers
    -0.70
    POSITIVE LOGITS
    less
    0.60
     of
    0.48
     verba
    0.47
    ikation
    0.46
    ství
    0.46
    ar
    0.45
     selanjutnya
    0.45
     هيا
    0.45
    way
    0.45
    plan
    0.44
    Activations Density 0.190%

    No Known Activations