© 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. 4011
    Prev
    Next
    INDEX
    Explanations

    3

    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
    Espèce
    -0.56
     décédé
    -0.53
    ViewFeatures
    -0.52
    IVEREF
    -0.52
     "..\..\
    -0.52
     initComponents
    -0.51
    AttributeSet
    -0.51
    يتها
    -0.49
    thod
    -0.48
    matchCondition
    -0.47
    POSITIVE LOGITS
     ModelExpression
    0.75
    neo
    0.62
    family
    0.60
     виправивши
    0.59
    tvguidetime
    0.57
     family
    0.56
    Family
    0.55
    Neo
    0.54
    Rptr
    0.54
    Демографія
    0.52
    Activations Density 0.003%

    No Known Activations