© 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. 4-CLT-HP
    7. 5022
    Prev
    Next
    INDEX
    Explanations

    Code and formal writing

    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
    IntoConstraints
    -0.61
     ویکی‌پدیا
    -0.59
     otomatig
    -0.58
    tadır
    -0.56
     فريبيس
    -0.50
    volezza
    -0.50
    ьаж
    -0.49
     Abp
    -0.49
    chymal
    -0.49
    ragalactic
    -0.48
    POSITIVE LOGITS
     time
    0.72
     Paglinawan
    0.57
    spring
    0.50
    skim
    0.48
    Hozzáférés
    0.48
    time
    0.47
     Spring
    0.47
     SPRING
    0.46
     TIME
    0.46
    timedelta
    0.46
    Activations Density 0.001%

    No Known Activations