© 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. 96741
    Prev
    Next
    INDEX
    Explanations

    as or called

    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
     AssemblyCompany
    -0.57
    ScopeManager
    -0.56
    期刊论文
    -0.54
    ゴリー
    -0.52
    الإنجليزية
    -0.52
    rich
    -0.49
    WaitGroup
    -0.49
    my
    -0.49
    abetes
    -0.48
    Erreferentziak
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.70
     للاسماء
    0.64
     Réponses
    0.63
    észetes
    0.62
     Numerade
    0.61
     Reisedaten
    0.60
    省市镇
    0.57
    ArrowToggle
    0.56
    Демографія
    0.55
    ContentAsync
    0.54
    Activations Density 0.000%

    No Known Activations