© 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. 97185
    Prev
    Next
    INDEX
    Explanations

    rine

    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
     débats
    -0.52
    |')
    -0.50
    "};
    -0.50
    WriteTagHelper
    -0.49
    uete
    -0.48
    roek
    -0.46
    %);
    -0.46
    ynos
    -0.45
    WebServlet
    -0.44
    __);
    -0.44
    POSITIVE LOGITS
    principalTable
    0.64
     Efq
    0.62
     referenties
    0.57
     creations
    0.55
    windowFixed
    0.54
     himſelf
    0.54
     Ceramby
    0.54
    Билгалдахарш
    0.53
     alloys
    0.52
    '
    0.52
    Activations Density 0.000%

    No Known Activations