© 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. 1-CLT-HP
    7. 45553
    Prev
    Next
    INDEX
    Explanations

    General text/filler words

    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
    AnimationsModule
    -0.55
    urlencoded
    -0.55
    AnchorStyles
    -0.54
    MeasureSpec
    -0.50
     reflejo
    -0.47
    formKey
    -0.47
     NavController
    -0.46
     lot
    -0.46
     présidenti
    -0.46
     clés
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    0.65
     صوتيه
    0.62
    featureID
    0.61
    TintMode
    0.60
    most
    0.58
     ffilmiau
    0.57
     getRule
    0.56
     wireType
    0.55
     most
    0.55
     financeira
    0.54
    Activations Density 0.003%

    No Known Activations