© 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. 0-CLT-HP
    7. 94284
    Prev
    Next
    INDEX
    Explanations

    ystic

    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
     dropped
    -0.66
     createSlice
    -0.63
    HandlerContext
    -0.62
    انجليز
    -0.60
    Dropped
    -0.59
     Wharf
    -0.58
    runApp
    -0.57
    Välislingid
    -0.56
     հղումներ
    -0.56
    ystic
    -0.56
    POSITIVE LOGITS
    jsonwebtoken
    0.56
    zins
    0.53
    unculus
    0.48
    види
    0.48
    blauch
    0.47
    ilid
    0.45
    schen
    0.43
    trad
    0.43
    комо
    0.42
    oque
    0.42
    Activations Density 0.106%

    No Known Activations