© 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. 0-CLT-HP
    7. 94257
    Prev
    Next
    INDEX
    Explanations

    government, intelligence, supply, psychology

    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
    ⓧ
    -0.91
    MigrationBuilder
    -0.84
    UserScript
    -0.77
    RenderAtEndOf
    -0.76
    +:+
    -0.75
     pinulongan
    -0.73
     Roskov
    -0.73
    Autoritní
    -0.72
     Supply
    -0.72
     насељу
    -0.72
    POSITIVE LOGITS
     Cou
    0.56
     Lag
    0.47
     Kal
    0.45
     Cut
    0.44
     Clock
    0.44
    kond
    0.44
     Cul
    0.43
     Dies
    0.42
     Cos
    0.42
     corre
    0.42
    Activations Density 0.301%

    No Known Activations