© 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. 1-CLT-HP
    7. 977
    Prev
    Next
    INDEX
    Explanations

    now

    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
     aveug
    -0.55
     now
    -0.54
     ouvertes
    -0.49
     maintenant
    -0.47
    ขาว
    -0.46
     Bezos
    -0.45
     ajuns
    -0.45
     rabies
    -0.45
     désormais
    -0.42
     vincere
    -0.42
    POSITIVE LOGITS
     الحره
    0.74
    webElementXpaths
    0.63
    gether
    0.63
     ModelExpression
    0.63
    hold
    0.62
    writeFieldEnd
    0.62
     numberWith
    0.61
    adays
    0.60
     wireType
    0.59
    ise
    0.59
    Activations Density 0.028%

    No Known Activations