© 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. 40320
    Prev
    Next
    INDEX
    Explanations

    surprise, upset

    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
     surprise
    -1.54
     overras
    -1.41
     surprised
    -1.34
    surprise
    -1.32
     sudden
    -1.27
     sorpresa
    -1.22
     surpresa
    -1.22
     Surprise
    -1.19
     surprises
    -1.17
    Surprise
    -1.17
    POSITIVE LOGITS
    awaiter
    0.70
    ibatis
    0.59
    multer
    0.58
    ScopeManager
    0.57
     in
    0.52
     form
    0.51
    AccessorTable
    0.51
    (!__
    0.51
    ]--;
    0.50
    ImageContext
    0.50
    Activations Density 0.025%

    No Known Activations