© 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. 0-CLT-HP
    7. 92598
    Prev
    Next
    INDEX
    Explanations

    Copying and transactions

    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
    stateProvider
    -0.51
     (
    -0.48
    ensement
    -0.48
     so
    -0.48
     C
    -0.47
     R
    -0.45
     a
    -0.44
     OR
    -0.44
     too
    -0.44
     non
    -0.43
    POSITIVE LOGITS
     متعلقه
    0.88
     itſelf
    0.77
     referenties
    0.75
     Silurian
    0.74
     Caspian
    0.71
    parsedMessage
    0.71
     Josephus
    0.69
     reaſon
    0.68
     Paglinawan
    0.68
     незавершена
    0.68
    Activations Density 0.039%

    No Known Activations