© 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. 20-CLT-HP
    4. 75232
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    rotating
    -0.61
     MessageBoxIcon
    -0.60
    localctx
    -0.59
    Turning
    -0.59
     Fli
    -0.59
     Turning
    -0.58
     fédé
    -0.57
     igång
    -0.57
     Partagez
    -0.57
    LabelTagHelper
    -0.57
    POSITIVE LOGITS
    ViewFeatures
    0.55
     مشين
    0.54
    tep
    0.54
    MethodManager
    0.49
    step
    0.49
     step
    0.49
     Ente
    0.48
    brokes
    0.47
    Service
    0.47
     kasarigan
    0.44
    Activations Density 0.001%

    No Known Activations