© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73633
    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
    ToAction
    -0.74
    awtextra
    -0.63
    styleType
    -0.63
    клопе
    -0.58
     <=",
    -0.57
    -------
    -0.57
    ViewImports
    -0.55
    AddTagHelper
    -0.54
    AntiForgeryToken
    -0.54
     ExecuteAsync
    -0.52
    POSITIVE LOGITS
    timeScale
    0.46
    swald
    0.45
     huyện
    0.45
    Shrink
    0.45
    __(/*!
    0.43
     emplois
    0.43
     turns
    0.42
    roves
    0.42
     rong
    0.42
     beats
    0.42
    Activations Density 0.015%

    No Known Activations