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. 11255
    Prev
    Next
    INDEX
    Explanations

    SL

    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
    +#+
    -0.73
    +:+
    -0.52
     Donahue
    -0.50
    ttino
    -0.48
     "..\..\..\
    -0.48
     Fot
    -0.47
     مشين
    -0.47
     tuong
    -0.44
    thumbnails
    -0.44
    korn
    -0.44
    POSITIVE LOGITS
    saraba
    0.73
     to
    0.71
     CreateTagHelper
    0.63
     autorytatywna
    0.60
    sizeCache
    0.57
    المشاركات
    0.55
    gouv
    0.54
    CloseOperation
    0.53
     unto
    0.52
    ViewImports
    0.52
    Activations Density 0.035%

    No Known Activations