© 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. 1-CLT-HP
    7. 9500
    Prev
    Next
    INDEX
    Explanations

    Code/HTML snippets

    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
    bour
    -0.77
    chool
    -0.50
    findpost
    -0.47
    uesa
    -0.46
    ")))
    -0.46
     ***!
    -0.46
    hofen
    -0.45
    ettet
    -0.44
    requent
    -0.43
     vulgaires
    -0.43
    POSITIVE LOGITS
     NDEBUG
    0.71
    didSet
    0.65
    клопе
    0.64
     BorderRadius
    0.60
    RSpec
    0.59
    DataAnnotations
    0.58
    sper
    0.53
     esternos
    0.53
    RuleContext
    0.53
    contre
    0.53
    Activations Density 0.005%

    No Known Activations