© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43754
    Prev
    Next
    INDEX
    Explanations

    where

    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
     löyty
    -0.56
     sẻ
    -0.53
     térm
    -0.52
    ıştır
    -0.52
    makeText
    -0.51
    ukseen
    -0.51
     destes
    -0.51
     keskus
    -0.50
     szczy
    -0.50
     lèvres
    -0.49
    POSITIVE LOGITS
     he
    0.72
     various
    0.69
    tvguidetime
    0.68
     numerous
    0.61
     a
    0.59
     the
    0.57
    IndentedString
    0.57
     ostavi
    0.56
     she
    0.56
     little
    0.56
    Activations Density 0.367%

    No Known Activations