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. 11069
    Prev
    Next
    INDEX
    Explanations

    Includes "Kra" or similar words

    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
    uating
    -0.94
    ThroughAttribute
    -0.82
    WireFormatLite
    -0.69
    WebElementEntity
    -0.63
     Meksiku
    -0.63
     UFO
    -0.62
    tagHelperRunner
    -0.60
     aDecoder
    -0.60
     disambiguazione
    -0.60
     AspNetCore
    -0.60
    POSITIVE LOGITS
     NACIONAL
    0.48
     leia
    0.47
     instr
    0.45
    medriver
    0.44
    its
    0.43
    üße
    0.43
     owne
    0.42
    ceiling
    0.42
     تانيه
    0.41
    le
    0.41
    Activations Density 0.015%

    No Known Activations