© 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. 1-CLT-HP
    7. 14793
    Prev
    Next
    INDEX
    Explanations

    regulations

    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
    yar
    -0.54
     linear
    -0.54
    leetcode
    -0.53
    footnote
    -0.52
    localctx
    -0.52
     poveznice
    -0.50
     ExecuteAsync
    -0.50
    婿
    -0.48
    ();)
    -0.47
     Rechts
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.66
    //
    0.63
    Personensuche
    0.58
    NOPQRST
    0.56
    enderror
    0.54
    ंदीखरीदारी
    0.52
    RTEX
    0.52
     CURIAM
    0.52
    ကိုးကား
    0.51
    Literatura
    0.50
    Activations Density 0.003%

    No Known Activations