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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74080
    Prev
    Next
    INDEX
    Explanations

    technical documents and websites

    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
     ویکی‌پدیای
    -0.50
     flori
    -0.47
     danse
    -0.46
    mainAxisSize
    -0.44
     destroying
    -0.44
     contre
    -0.44
    újo
    -0.43
    ("$.
    -0.43
     Référence
    -0.42
     wrecked
    -0.42
    POSITIVE LOGITS
     HasFactory
    0.77
     AspNetCore
    0.71
     الحره
    0.71
     AttributeSet
    0.65
     oprot
    0.65
     saites
    0.60
    تقاوى
    0.60
    LookAnd
    0.59
     makeStyles
    0.57
    IUrlHelper
    0.56
    Activations Density 0.000%

    No Known Activations