© 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. 5-CLT-HP
    7. 90881
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "word"

    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
    -0.82
     surla
    -0.69
    IBOutlet
    -0.67
     BoxDecoration
    -0.65
    urlpatterns
    -0.64
    Tembelea
    -0.63
     createSlice
    -0.63
    IsPostBack
    -0.62
    PreferredItem
    -0.61
    MessageOf
    -0.61
    POSITIVE LOGITS
     rare
    0.46
    EndContext
    0.45
     McDon
    0.44
     locu
    0.44
     pair
    0.42
    basicConfig
    0.42
     pinulongan
    0.42
     Telex
    0.40
    Heer
    0.40
    كويكب
    0.40
    Activations Density 0.039%

    No Known Activations