© 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. 0-CLT-HP
    7. 1902
    Prev
    Next
    INDEX
    Explanations

    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
    bindParam
    -0.63
    věř
    -0.56
    tvguidetime
    -0.55
    ตาย
    -0.55
    protoc
    -0.54
    BeginContext
    -0.52
    arthed
    -0.52
    TargetException
    -0.52
    WebVitals
    -0.51
    AnchorTagHelper
    -0.50
    POSITIVE LOGITS
     Ragnar
    0.63
     Athenians
    0.57
    RetentionPolicy
    0.54
     Puritan
    0.53
     Rembrandt
    0.53
     övers
    0.53
     Dost
    0.53
     reca
    0.53
     Puritans
    0.53
     Romans
    0.52
    Activations Density 0.011%

    No Known Activations