© 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. 42317
    Prev
    Next
    INDEX
    Explanations

    positive adjectives

    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
     psicológica
    -0.78
     prêtres
    -0.74
     Económica
    -0.74
     enfans
    -0.73
     judiciaire
    -0.70
     feroit
    -0.69
     étoient
    -0.69
     Majestic
    -0.69
     étoit
    -0.68
     avoient
    -0.68
    POSITIVE LOGITS
    ally
    0.70
     Ten
    0.58
     Club
    0.53
    AspNetCore
    0.53
    LY
    0.52
    !")
    0.52
    ly
    0.52
     Al
    0.52
     Centre
    0.52
    ALLY
    0.51
    Activations Density 0.057%

    No Known Activations