© 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. 94711
    Prev
    Next
    INDEX
    Explanations

    heroes and deities

    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
     hero
    -1.21
    hero
    -0.70
     Hero
    -0.69
     heroes
    -0.66
    Hero
    -0.62
     héroe
    -0.58
     герой
    -0.57
    Heroes
    -0.55
     героя
    -0.54
     Heroes
    -0.53
    POSITIVE LOGITS
     fondament
    0.73
     contextLoads
    0.70
     ſtate
    0.69
    ſelf
    0.66
    Xna
    0.66
    InputBorder
    0.66
    GEBURTSDATUM
    0.66
     Jefus
    0.65
     perſon
    0.65
     deschis
    0.64
    Activations Density 0.700%

    No Known Activations