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. 12934
    Prev
    Next
    INDEX
    Explanations

    believe

    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
     mergul
    -0.47
    ContentAlignment
    -0.45
     News
    -0.44
    WebElementEntity
    -0.44
    contentLoaded
    -0.41
     Naples
    -0.41
     Mile
    -0.40
     étages
    -0.40
     Mention
    -0.40
    neos
    -0.40
    POSITIVE LOGITS
    IntoConstraints
    0.68
     that
    0.68
     doInBackground
    0.63
    \{\\
    0.60
    awtextra
    0.59
    queryInterface
    0.59
    VersionUID
    0.57
    makeConstraints
    0.57
    KommentareTeilen
    0.57
    BeginContext
    0.57
    Activations Density 0.035%

    No Known Activations