© 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. 5-CLT-HP
    7. 92311
    Prev
    Next
    INDEX
    Explanations

    instructions, lists, arrangements

    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
    })));
    -0.66
     />";
    -0.61
    Hentet
    -0.59
    ++.
    -0.58
    ...');
    -0.56
    abetes
    -0.56
    bitField
    -0.54
    RenderAtEndOf
    -0.54
    unately
    -0.52
     woe
    -0.52
    POSITIVE LOGITS
     الحره
    0.63
     المعيارى
    0.60
     تضيفلها
    0.56
    gbaar
    0.52
    AndEndTag
    0.49
     Commencez
    0.48
    rinfo
    0.47
    TintMode
    0.47
     mensuales
    0.46
    gement
    0.46
    Activations Density 0.001%

    No Known Activations