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. 1-CLT-HP
    4. 11043
    Prev
    Next
    INDEX
    Explanations

    organizations and government, SEC

    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
    osan
    -0.77
     Gug
    -0.53
    omeness
    -0.50
    RLock
    -0.46
    bited
    -0.46
    Naissance
    -0.46
     chóng
    -0.45
    anmoins
    -0.45
    ISupport
    -0.44
    tanleria
    -0.44
    POSITIVE LOGITS
     tromper
    0.61
     InputDecoration
    0.59
    HasAnnotation
    0.55
    الإنجليزية
    0.54
    ць
    0.53
    AddTagHelper
    0.52
    findpost
    0.52
    zeiger
    0.50
     ?>/
    0.50
    utiful
    0.50
    Activations Density 0.007%

    No Known Activations