© 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. 0-CLT-HP
    7. 43785
    Prev
    Next
    INDEX
    Explanations

    importance

    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
     essential
    -1.18
    essential
    -1.15
     essentielles
    -1.03
     essentiel
    -1.02
     essentielle
    -1.02
     esenciales
    -0.98
     esencial
    -0.94
     essencial
    -0.93
     essenziale
    -0.93
    Essential
    -0.89
    POSITIVE LOGITS
    writeFieldEnd
    0.77
     BoxFit
    0.75
    
    0.72
     OGS
    0.65
    retweeted
    0.62
    IsContent
    0.60
    homemade
    0.60
     Superhost
    0.60
     Baillargeon
    0.59
     "..\..\..\
    0.59
    Activations Density 0.100%

    No Known Activations