© 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. 3410
    Prev
    Next
    INDEX
    Explanations

    single digit numbers

    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
    -}
    -0.50
    DOM
    -0.50
    -
    -0.47
    Point
    -0.44
    PT
    -0.41
     
    -0.41
    -%
    -0.40
    ome
    -0.40
    AnchorTagHelper
    -0.40
    ish
    -0.39
    POSITIVE LOGITS
     насељу
    0.81
     ExecuteAsync
    0.68
    MigrationBuilder
    0.68
    Tikang
    0.62
    obald
    0.60
    Tembelea
    0.59
     propOrder
    0.59
     MenuView
    0.59
     MotionEvent
    0.59
    exitRule
    0.59
    Activations Density 0.006%

    No Known Activations