© 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. 5-CLT-HP
    7. 1024
    Prev
    Next
    INDEX
    Explanations

    Uncertainty/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
     nakalista
    -0.74
     שוליים
    -0.73
    httphttps
    -0.68
     समीक्षाओं
    -0.67
     surla
    -0.65
     otomatig
    -0.63
    AddTagHelper
    -0.63
     صوتيه
    -0.62
     Réponses
    -0.62
    WebElementEntity
    -0.61
    POSITIVE LOGITS
     the
    0.67
    autoIncrement
    0.50
    udadera
    0.47
    Suits
    0.45
    wußt
    0.45
     Yus
    0.44
    suits
    0.44
    OWA
    0.44
     Gewähr
    0.43
    GetBytes
    0.43
    Activations Density 0.001%

    No Known Activations