© 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. 1-CLT-HP
    7. 10400
    Prev
    Next
    INDEX
    Explanations

    as a whole, such

    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
    numerusform
    -0.61
     precisione
    -0.60
    )");
    -0.57
     nôtre
    -0.57
     démocratie
    -0.56
     vœux
    -0.56
     régulière
    -0.56
     côtés
    -0.55
     chré
    -0.55
     réguli
    -0.55
    POSITIVE LOGITS
    LookAnd
    0.66
     AssemblyProduct
    0.54
    TintMode
    0.52
    énario
    0.52
    phosa
    0.51
    pidou
    0.51
    antation
    0.49
     stork
    0.49
    audiovisuel
    0.49
    милия
    0.48
    Activations Density 0.057%

    No Known Activations