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. 20-CLT-HP
    4. 74190
    Prev
    Next
    INDEX
    Explanations

    Code and uncommon languages

    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
     nahilalakip
    -0.56
    Chham
    -0.55
    Rhestr
    -0.54
     ویکی‌پدیا
    -0.54
     iprot
    -0.54
    ſelf
    -0.53
    vereignty
    -0.53
    writeField
    -0.53
    bergement
    -0.52
     Adhe
    -0.50
    POSITIVE LOGITS
     gọn
    0.54
     MainAxisSize
    0.53
    roco
    0.44
     May
    0.44
    루
    0.44
    الحياه
    0.43
    /*
    0.43
     comme
    0.42
    Geplaatst
    0.41
    Chú
    0.41
    Activations Density 0.002%

    No Known Activations