© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4364
    Prev
    Next
    INDEX
    Explanations

    correctness

    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
    SourceChecksum
    -0.70
    :])
    -0.54
    migrationBuilder
    -0.54
    RegressionTest
    -0.54
    tahui
    -0.53
    makeText
    -0.52
    //
    -0.52
    Nuorodos
    -0.51
     cherchés
    -0.49
     initComponents
    -0.49
    POSITIVE LOGITS
     result
    0.57
     features
    0.56
     feature
    0.53
    ustes
    0.53
     emotions
    0.53
     form
    0.52
     characteristics
    0.52
     choices
    0.52
    OwnProperty
    0.52
     type
    0.50
    Activations Density 0.004%

    No Known Activations