© 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. 91067
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency

    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
     nahilalakip
    -0.60
    حياته
    -0.54
     pregnant
    -0.53
     Administrativna
    -0.47
    iotensin
    -0.47
     Pregnant
    -0.47
    ysław
    -0.47
    yce
    -0.45
     udaler
    -0.43
    PerformLayout
    -0.43
    POSITIVE LOGITS
     you
    0.78
    IsContent
    0.63
    μως
    0.62
     sondern
    0.62
     propOrder
    0.60
     they
    0.59
     we
    0.54
     companies
    0.54
     ustedes
    0.54
     questions
    0.53
    Activations Density 0.002%

    No Known Activations