© 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. 94424
    Prev
    Next
    INDEX
    Explanations

    animal

    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
     animal
    -1.07
     Animal
    -0.90
     Horse
    -0.89
    animal
    -0.87
    ve
    -0.86
     horse
    -0.81
    Animal
    -0.79
    Horse
    -0.77
     ve
    -0.73
     in
    -0.72
    POSITIVE LOGITS
     Monfieur
    1.27
     Reſ
    1.16
     Majefty
    1.12
     Efq
    1.12
     itſelf
    1.12
     Anſ
    1.11
     houſe
    1.09
     Houſe
    1.08
     purpoſe
    1.07
     ſeveral
    1.07
    Activations Density 0.727%

    No Known Activations