© 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. 9630
    Prev
    Next
    INDEX
    Explanations

    names and scientific terms

    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
    sspiel
    -0.65
    machus
    -0.54
     vivant
    -0.54
     MessageBoxIcon
    -0.51
    --){
    -0.50
     privées
    -0.50
    //
    -0.50
    latform
    -0.49
    contentLoaded
    -0.49
     grave
    -0.49
    POSITIVE LOGITS
    ensement
    0.56
    Derbyniad
    0.54
     smer
    0.54
    NOPQRST
    0.52
     pubb
    0.50
    -------------</
    0.49
    ferrer
    0.49
    нодоро
    0.47
    UserScript
    0.47
    lagos
    0.46
    Activations Density 0.012%

    No Known Activations