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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97839
    Prev
    Next
    INDEX
    Explanations

    holidays and time

    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
    <bos>
    -0.73
    WebVitals
    -0.68
    UserScript
    -0.67
    ThroughAttribute
    -0.65
     Jefus
    -0.64
    forRoot
    -0.63
     Motto
    -0.63
    MongoClient
    -0.62
     itſelf
    -0.61
     Chriſt
    -0.60
    POSITIVE LOGITS
     Weekend
    0.52
    ArgsConstructor
    0.50
     weekend
    0.46
     WEEKEND
    0.43
    Weekend
    0.43
    alada
    0.42
     Daley
    0.42
    '].'
    0.41
     weekends
    0.41
    urez
    0.40
    Activations Density 0.008%

    No Known Activations