© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8889
    Prev
    Next
    INDEX
    Explanations

    movies

    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
    Negative Logits
    expandindo
    -0.79
    basicConfig
    -0.70
     ddelweddau
    -0.69
    terase
    -0.67
    gonic
    -0.67
    RectangleBorder
    -0.65
    ciclopedia
    -0.65
    брь
    -0.61
    cences
    -0.60
     Biôgrafia
    -0.59
    POSITIVE LOGITS
     movie
    0.99
     film
    0.92
     films
    0.84
     movies
    0.82
    movie
    0.81
     Movie
    0.81
     cinematogra
    0.79
    Movie
    0.78
    Films
    0.78
     Movies
    0.76
    Activations Density 0.006%

    No Known Activations