© 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. 4-CLT-HP
    7. 1925
    Prev
    Next
    INDEX
    Explanations

    against

    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
     termica
    -0.61
     réserv
    -0.54
     indépendante
    -0.49
    المشاركات
    -0.49
     résist
    -0.48
     prière
    -0.48
     automatiques
    -0.48
     față
    -0.48
     strto
    -0.47
     suscripción
    -0.47
    POSITIVE LOGITS
    AddTagHelper
    0.68
     too
    0.62
    EDEFAULT
    0.62
     ever
    0.61
     externi
    0.59
    MMdd
    0.58
     over
    0.57
     sterile
    0.56
    ">+
    0.55
    basicConfig
    0.54
    Activations Density 0.002%

    No Known Activations