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. 0-CLT-HP
    4. 40833
    Prev
    Next
    INDEX
    Explanations

    SE

    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
     SE
    -0.81
     Bio
    -0.58
    tail
    -0.51
     مشارکت‌کنندگان
    -0.47
    oluzione
    -0.46
     bio
    -0.46
    CustomAttributes
    -0.46
    olto
    -0.46
    EXPECT
    -0.45
    uary
    -0.44
    POSITIVE LOGITS
    InSection
    0.60
    ilets
    0.58
     surla
    0.56
    audiovisuel
    0.55
    dehyde
    0.54
    lippe
    0.53
    dresser
    0.53
    apunov
    0.53
     désolés
    0.53
    RenderAtEndOf
    0.52
    Activations Density 0.652%

    No Known Activations