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. 11078
    Prev
    Next
    INDEX
    Explanations

    nonatomic

    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
    RegressionTest
    -0.64
    +#+#
    -0.56
    parsedMessage
    -0.54
     مرئيه
    -0.52
    /*
    -0.52
    databind
    -0.50
    sizeCache
    -0.49
     kasarigan
    -0.49
    SizedBox
    -0.48
    NamedQueries
    -0.47
    POSITIVE LOGITS
    ItemBackground
    0.58
     saurait
    0.56
     készült
    0.55
    êté
    0.53
    umbledore
    0.53
     desaf
    0.53
    pertino
    0.53
     alapján
    0.53
    @"
    0.52
     extinct
    0.52
    Activations Density 2.679%

    No Known Activations