© 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. 40639
    Prev
    Next
    INDEX
    Explanations

    document headers

    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
     Numerade
    -0.52
    perPage
    -0.52
    Raf
    -0.50
    सन्दर्भ
    -0.48
    hdessä
    -0.48
    numerusform
    -0.47
     tricks
    -0.47
    pitaux
    -0.46
    iliary
    -0.45
    sky
    -0.45
    POSITIVE LOGITS
     Meksiku
    0.85
    parsedMessage
    0.78
     resourceCulture
    0.75
    sidemargin
    0.68
    localctx
    0.67
     Chwiliwch
    0.64
    stateProvider
    0.63
     wireType
    0.62
     ModelExpression
    0.62
    发表于
    0.62
    Activations Density 0.114%

    No Known Activations