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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12718
    Prev
    Next
    INDEX
    Explanations

    lore

    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
     nahilalakip
    -0.94
    enumi
    -0.79
    сылкі
    -0.77
    UIControlState
    -0.75
    awtextra
    -0.70
     mukana
    -0.69
     lenker
    -0.69
    ThroughAttribute
    -0.68
     OMIT
    -0.66
     Мексичка
    -0.66
    POSITIVE LOGITS
     Lexer
    0.44
    jfree
    0.42
    jem
    0.42
     cevap
    0.41
    ContainsKey
    0.40
    webhook
    0.40
    naeus
    0.39
    ia
    0.39
    io
    0.38
    桌上
    0.38
    Activations Density 0.075%

    No Known Activations