© 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. 41414
    Prev
    Next
    INDEX
    Explanations

    beauty

    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
     beautiful
    -1.17
    beautiful
    -1.05
     gorgeous
    -0.97
     beauty
    -0.96
     brilliant
    -0.94
    Beautiful
    -0.93
     Beautiful
    -0.88
    beauty
    -0.88
    gorgeous
    -0.84
     wundersch
    -0.81
    POSITIVE LOGITS
     Crimean
    0.64
     Assyrian
    0.63
     poffe
    0.60
     exaggeration
    0.59
    :✨
    0.59
    yntaxException
    0.59
    󠁢
    0.57
     MainAxisSize
    0.56
     Fascism
    0.56
     itſelf
    0.55
    Activations Density 0.139%

    No Known Activations