© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42353
    Prev
    Next
    INDEX
    Explanations

    Academic/Formal writing

    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
     noqa
    -0.78
     ligiloj
    -0.67
    MLLoader
    -0.58
    udesta
    -0.57
     mergeFrom
    -0.57
     Styled
    -0.56
     purpoſe
    -0.56
     formatting
    -0.55
     geweest
    -0.55
     Format
    -0.54
    POSITIVE LOGITS
    atguigu
    0.54
    ellas
    0.50
    метри
    0.47
     CYTHON
    0.47
    нку
    0.47
    DeleteCommand
    0.47
    bed
    0.46
    siti
    0.46
    neti
    0.45
    appartamento
    0.45
    Activations Density 0.355%

    No Known Activations