© 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. 4-CLT-HP
    7. 4942
    Prev
    Next
    INDEX
    Explanations

    preparation

    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
    はじめに
    -0.66
    出版年
    -0.62
    المكان
    -0.58
    曖昧さ回避
    -0.54
    MIDDLEWARE
    -0.52
    GEBURTSDATUM
    -0.52
     通販
    -0.52
    paramref
    -0.50
     Magi
    -0.50
    daille
    -0.50
    POSITIVE LOGITS
     celebrating
    0.65
     keeping
    0.63
     commemorating
    0.61
     propOrder
    0.60
    acaktır
    0.59
     maintaining
    0.59
     bezeichneter
    0.56
     honoring
    0.54
     continues
    0.53
    RenderAtEndOf
    0.53
    Activations Density 0.003%

    No Known Activations