© 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. 5-CLT-HP
    7. 965
    Prev
    Next
    INDEX
    Explanations

    dates, data, and code

    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
    romatic
    -0.49
    ModelMap
    -0.46
    citi
    -0.44
     organic
    -0.44
     large
    -0.44
    pus
    -0.44
     thought
    -0.43
     treasury
    -0.43
     fine
    -0.43
     parallax
    -0.43
    POSITIVE LOGITS
    MigrationBuilder
    0.81
     OFDb
    0.75
     kaarangay
    0.71
    XmlAccessorType
    0.70
    ьаж
    0.70
    GEBURTSDATUM
    0.69
    rungsseite
    0.69
     виправивши
    0.68
    providedIn
    0.67
    RegressionTest
    0.65
    Activations Density 0.144%

    No Known Activations