© 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. 4-CLT-HP
    7. 4582
    Prev
    Next
    INDEX
    Explanations

    table data structures

    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
     تضيفلها
    -0.78
    évaluateur
    -0.73
    
    -0.71
    出版年
    -0.67
    WindowConstants
    -0.62
     الحره
    -0.61
    findpost
    -0.60
     חיצוניים
    -0.59
    WebVitals
    -0.56
    OGND
    -0.55
    POSITIVE LOGITS
     numberOfRows
    0.58
     headers
    0.57
    headers
    0.53
    ToLower
    0.51
    itteet
    0.48
     JTable
    0.48
    Ingrédients
    0.47
    sig
    0.46
     header
    0.46
     metadata
    0.46
    Activations Density 0.023%

    No Known Activations