© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 839
    Prev
    Next
    INDEX
    Explanations

    tanger

    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
     الحره
    -0.58
    migrationBuilder
    -0.54
     Geller
    -0.52
    runApp
    -0.51
    addContainerGap
    -0.51
     ostavi
    -0.50
    ])));
    -0.50
    ResponseWriter
    -0.49
    urlpatterns
    -0.48
    はじめに
    -0.48
    POSITIVE LOGITS
    a
    0.87
    e
    0.79
    i
    0.65
    ly
    0.62
    ade
    0.60
    s
    0.60
    l
    0.58
    t
    0.57
    lli
    0.55
     transférez
    0.54
    Activations Density 0.015%

    No Known Activations