© 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. 5-CLT-HP
    7. 97329
    Prev
    Next
    INDEX
    Explanations

    wood

    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
    uver
    -0.60
    AndView
    -0.50
    SourceChecksum
    -0.49
    Tikang
    -0.47
     toc
    -0.46
    wili
    -0.45
    :✨
    -0.45
    umers
    -0.44
    μπ
    -0.44
    Doc
    -0.44
    POSITIVE LOGITS
     BorderSide
    0.62
     Audiodateien
    0.60
     فريبيس
    0.56
     GoogleFonts
    0.55
    ActionCreators
    0.54
     onAnimation
    0.54
    AttributeSet
    0.53
    InputBorder
    0.53
    ագրություններ
    0.50
    fromnode
    0.50
    Activations Density 0.000%

    No Known Activations