© 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. 15715
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     Gloucester
    -1.10
     ब्रेकडाउन
    -0.67
    cester
    -0.50
     Gloucestershire
    -0.50
    ReusableCell
    -0.47
     Pentagon
    -0.47
     onCreateView
    -0.46
     caoutchouc
    -0.46
    er
    -0.46
    //
    -0.46
    POSITIVE LOGITS
    Personendaten
    0.68
    cana
    0.64
     transfieras
    0.61
     Wea
    0.59
    WriteTagHelper
    0.57
     SwiftUI
    0.53
    脚注の使い方
    0.53
     nahilalakip
    0.53
    WindowConstants
    0.53
    udesta
    0.51
    Activations Density 0.003%

    No Known Activations