© 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. 42665
    Prev
    Next
    INDEX
    Explanations

    Legal/technical documents

    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
    клопе
    -0.89
     שוליים
    -0.88
    ainville
    -0.81
    ValueStyle
    -0.73
     ProtoMessage
    -0.70
    vinas
    -0.68
    principalColumn
    -0.67
    titleMargin
    -0.66
    migrationBuilder
    -0.64
     ujednoznacz
    -0.63
    POSITIVE LOGITS
    URLException
    0.56
     élector
    0.50
    enite
    0.50
     sauvages
    0.50
     humaines
    0.50
     ruch
    0.48
     empathi
    0.48
    hematical
    0.47
    doPost
    0.47
     leña
    0.47
    Activations Density 1.619%

    No Known Activations