© 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. 5-CLT-HP
    7. 92174
    Prev
    Next
    INDEX
    Explanations

    Dates/Years

    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
    ,‎
    -0.54
     chiens
    -0.52
     Beno
    -0.50
    yargs
    -0.49
    عن
    -0.46
    toBeDefined
    -0.46
     getRule
    -0.46
     Velvet
    -0.46
     Vie
    -0.45
     Yag
    -0.45
    POSITIVE LOGITS
    TintMode
    0.71
    StoryboardSegue
    0.66
     initComponents
    0.66
     AssemblyCulture
    0.61
    HasForeignKey
    0.60
    titleMargin
    0.58
    enment
    0.56
     transférez
    0.54
    تقاوى
    0.52
    hoeddwyd
    0.49
    Activations Density 0.001%

    No Known Activations