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. 11262
    Prev
    Next
    INDEX
    Explanations

    Sas

    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
    matchCondition
    -0.50
    IsContent
    -0.50
     ***!
    -0.49
    antee
    -0.49
     Santa
    -0.44
     pimiento
    -0.44
    perma
    -0.43
     final
    -0.43
     Sachsen
    -0.43
    ischer
    -0.43
    POSITIVE LOGITS
     âgées
    0.68
     fédé
    0.64
     détru
    0.64
     suprême
    0.64
     marié
    0.60
    cuál
    0.58
    تج
    0.57
     Cycle
    0.57
     épu
    0.57
     marquées
    0.56
    Activations Density 0.027%

    No Known Activations