© 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. 5-CLT-HP
    7. 3
    Prev
    Next
    INDEX
    Explanations

    mper

    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
    <bos>
    -0.57
     vPvB
    -0.52
    cshtml
    -0.50
     raiſ
    -0.49
     Приступљено
    -0.49
    Pois
    -0.48
    海道
    -0.47
    脚注の使い方
    -0.47
     prism
    -0.47
    tomos
    -0.47
    POSITIVE LOGITS
     bang
    0.73
     rush
    0.63
     فريبيس
    0.59
    bootstrapcdn
    0.57
     who
    0.56
    interopRequire
    0.56
     kteří
    0.56
     flourish
    0.56
     roar
    0.54
    Источники
    0.52
    Activations Density 0.022%

    No Known Activations