© 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. 0-CLT-HP
    7. 42020
    Prev
    Next
    INDEX
    Explanations

    hungry/eager

    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
     hungry
    -0.88
    hungry
    -0.80
     hunger
    -0.78
     thirst
    -0.75
     Hungry
    -0.75
    ume
    -0.71
    EDEFAULT
    -0.71
     thirsty
    -0.68
    Hungry
    -0.64
    hunger
    -0.63
    POSITIVE LOGITS
    Cartney
    0.69
     "..\..\..\
    0.60
     ویکی‌پدی
    0.59
    e
    0.58
     @"/
    0.57
    ceous
    0.53
    Carthy
    0.51
    ergic
    0.45
    ("}\
    0.44
    ionales
    0.41
    Activations Density 0.185%

    No Known Activations