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. 74068
    Prev
    Next
    INDEX
    Explanations

    groups/organizations

    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
    MigrationBuilder
    -0.72
     ModelExpression
    -0.70
     club
    -0.69
    :✨
    -0.64
    بوابة
    -0.63
     journalistes
    -0.61
    RegressionTest
    -0.60
     team
    -0.60
    odrome
    -0.60
     клуб
    -0.58
    POSITIVE LOGITS
     Companies
    0.71
     Corporations
    0.65
     companies
    0.65
     Commands
    0.64
     Bands
    0.63
     Associations
    0.62
     Districts
    0.62
     Unions
    0.62
     Colleges
    0.60
    Companies
    0.60
    Activations Density 0.007%

    No Known Activations