© 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. 20-CLT-HP
    7. 77697
    Prev
    Next
    INDEX
    Explanations

    Technical code and discussions

    np_max-act-logits · 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
    WithIOException
    -0.58
     setUsername
    -0.54
    jstor
    -0.54
     StringField
    -0.53
    stateProvider
    -0.52
    ignement
    -0.52
    TestTools
    -0.52
    isele
    -0.51
     Combien
    -0.49
    inspace
    -0.48
    POSITIVE LOGITS
    lan
    0.59
     Drops
    0.57
     drops
    0.56
    drops
    0.55
    AddTagHelper
    0.54
    lin
    0.54
    Drops
    0.54
     syrup
    0.53
     drop
    0.52
    Hauptartikel
    0.52
    Activations Density 0.003%

    No Known Activations