© 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. 4150
    Prev
    Next
    INDEX
    Explanations

    Cesare

    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
    :✨
    -0.68
    χος
    -0.60
     CURIAM
    -0.57
    GraphicsUnit
    -0.54
     Honour
    -0.48
    resor
    -0.48
    contentLoaded
    -0.48
    Semitic
    -0.48
     INTERESAR
    -0.43
     Worth
    -0.43
    POSITIVE LOGITS
    RegressionTest
    0.65
    CppMethod
    0.60
    databind
    0.56
    WriteTagHelper
    0.56
     ldc
    0.54
    migrationBuilder
    0.54
    URLConnection
    0.50
    pidou
    0.50
    expandindo
    0.49
    ">//
    0.49
    Activations Density 0.014%

    No Known Activations