© 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. 1753
    Prev
    Next
    INDEX
    Explanations

    approximations

    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
    Искәрмәләр
    -0.58
    sam
    -0.57
    SourceChecksum
    -0.57
    DoubleQuotes
    -0.55
    ագրություններ
    -0.55
    TypedDataSet
    -0.54
    TagHelper
    -0.51
     Meksiku
    -0.51
     estimés
    -0.51
    GGLE
    -0.50
    POSITIVE LOGITS
    følgelig
    0.64
    edback
    0.63
     myſelf
    0.62
    able
    0.61
    Abraço
    0.61
     незавершена
    0.60
     Jefus
    0.59
    leſs
    0.59
     itſelf
    0.58
     Efq
    0.58
    Activations Density 0.056%

    No Known Activations