© 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. 4-CLT-HP
    7. 405
    Prev
    Next
    INDEX
    Explanations

    visitors

    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
    atiche
    -0.61
    ftagPool
    -0.59
     समीक्षक
    -0.56
     Trọng
    -0.55
    Erreferentziak
    -0.54
    SBATCH
    -0.54
    ləş
    -0.52
    jewództ
    -0.51
     AssemblyCompany
    -0.51
    ysty
    -0.51
    POSITIVE LOGITS
     to
    1.52
    to
    0.68
     να
    0.60
    kuuta
    0.57
    tothe
    0.57
    참고
    0.56
    attendre
    0.56
     snapping
    0.54
    unknownFields
    0.52
     إلى
    0.52
    Activations Density 0.001%

    No Known Activations