© 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. 20-CLT-HP
    7. 77885
    Prev
    Next
    INDEX
    Explanations

    beginnings

    np_max-act-logits · 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
     World
    -0.98
    MigrationBuilder
    -0.93
    DockStyle
    -0.89
     WORLD
    -0.88
     CreateTagHelper
    -0.87
    World
    -0.86
     Waray
    -0.85
    WORLD
    -0.84
     WWII
    -0.83
     WW
    -0.82
    POSITIVE LOGITS
     First
    0.44
     turn
    0.41
     RCMP
    0.38
    turn
    0.37
     fous
    0.34
    OuterClass
    0.34
    First
    0.33
    قاء
    0.31
     aten
    0.31
    jeen
    0.30
    Activations Density 0.001%

    No Known Activations