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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11692
    Prev
    Next
    INDEX
    Explanations

    programming and websites

    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
     وتسجيلات
    -0.56
    ">//
    -0.50
    tagHelperRunner
    -0.49
    war
    -0.47
    rungsseite
    -0.47
    sm
    -0.46
    he
    -0.46
    dr
    -0.45
    ///</
    -0.45
     leão
    -0.45
    POSITIVE LOGITS
    tibus
    0.65
     referenties
    0.64
     itſelf
    0.62
     becauſe
    0.60
     Ressources
    0.60
    ชั้น
    0.59
    oOo
    0.56
     poffible
    0.56
    RetentionPolicy
    0.56
    FTFY
    0.55
    Activations Density 0.008%

    No Known Activations