© 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. 1-CLT-HP
    7. 15041
    Prev
    Next
    INDEX
    Explanations

    Aitken

    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
    ruth
    -0.52
     bole
    -0.49
     Coul
    -0.47
     Aitken
    -0.47
     leksikon
    -0.46
     Dodson
    -0.44
    かの
    -0.44
    muir
    -0.44
    vi
    -0.44
     vị
    -0.44
    POSITIVE LOGITS
     Италијани
    0.82
     виправивши
    0.79
    ismet
    0.73
     désolés
    0.73
     تانيه
    0.72
    WithIOException
    0.68
    AddTagHelper
    0.67
    NUMX
    0.67
    Vidite
    0.66
    Espèce
    0.65
    Activations Density 0.009%

    No Known Activations