© 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. 94991
    Prev
    Next
    INDEX
    Explanations

    animals

    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
     production
    -1.08
    Production
    -1.00
     Production
    -0.99
    production
    -0.99
     PRODUCTION
    -0.93
     producción
    -0.88
     produção
    -0.85
    PRODUCTION
    -0.81
    DockStyle
    -0.81
    findpost
    -0.81
    POSITIVE LOGITS
    elsen
    0.41
    mudi
    0.41
    caping
    0.41
     uttering
    0.41
     كذلك
    0.40
    ̵
    0.39
    setzer
    0.38
     ellers
    0.38
     impulso
    0.37
     navel
    0.36
    Activations Density 0.186%

    No Known Activations