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. 22-CLT-HP
    4. 74362
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    LookAnd
    -0.72
    RegistryLite
    -0.63
    WebElementEntity
    -0.63
    تفصیلات
    -0.62
    estacks
    -0.62
    aarrggbb
    -0.59
    MigrationBuilder
    -0.58
    ConstraintMaker
    -0.57
    Демографія
    -0.57
    IUrlHelper
    -0.57
    POSITIVE LOGITS
     Hill
    0.54
    SharedDtor
    0.50
    HIB
    0.48
     hill
    0.47
     d
    0.46
     D
    0.46
     Add
    0.44
    typeparam
    0.44
    Vaata
    0.43
    ếng
    0.43
    Activations Density 0.041%

    No Known Activations