© 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. 5-CLT-HP
    7. 93952
    Prev
    Next
    INDEX
    Explanations

    Negations

    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
    HtmlAttribute
    -0.55
     chiunque
    -0.53
     plastiques
    -0.53
    slidesPer
    -0.52
     that
    -0.51
     qualcuno
    -0.51
     ouvriers
    -0.50
    ;"></
    -0.48
    indest
    -0.48
     متعلقه
    -0.47
    POSITIVE LOGITS
    FunctionFlags
    0.61
     referenties
    0.60
     للاسماء
    0.57
     holds
    0.57
     hold
    0.57
    show
    0.57
    holds
    0.57
    vice
    0.57
    Geplaatst
    0.55
    Données
    0.55
    Activations Density 0.003%

    No Known Activations