© 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. 1499
    Prev
    Next
    INDEX
    Explanations

    {

    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
    TintMode
    -0.75
    addCriterion
    -0.73
    UnitTesting
    -0.70
    windowFixed
    -0.63
    ِّف
    -0.62
    ondheim
    -0.60
     Dandy
    -0.59
    titleMargin
    -0.59
    PreferredItem
    -0.58
    はじめに
    -0.57
    POSITIVE LOGITS
    MessageTagHelper
    0.85
    Fprintf
    0.55
    ⓧ
    0.52
     '{@
    0.51
    MENAFN
    0.49
    DOCTYPE
    0.48
     K
    0.47
    ாம
    0.47
    RoutingModule
    0.46
     profesión
    0.46
    Activations Density 1.870%

    No Known Activations