© 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. 4-CLT-HP
    7. 114
    Prev
    Next
    INDEX
    Explanations

    it

    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
    propTypes
    -0.55
    WillAppear
    -0.53
    ANTLR
    -0.52
    SequentialGroup
    -0.50
    ContentLoaded
    -0.48
    enderror
    -0.48
    UserScript
    -0.46
    กรรม
    -0.44
     costing
    -0.44
     bä
    -0.43
    POSITIVE LOGITS
    sizeCache
    0.62
     Himo
    0.59
    adaş
    0.58
    הערות
    0.58
    CloseOperation
    0.56
    الحياه
    0.56
    StreetMap
    0.55
    zun
    0.55
    yethyl
    0.54
    TextHelper
    0.52
    Activations Density 0.004%

    No Known Activations