© 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. 95731
    Prev
    Next
    INDEX
    Explanations

    habits and rituals

    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
    habit
    -0.85
     habit
    -0.78
     GenerationType
    -0.77
     nahilalakip
    -0.75
    WebElementEntity
    -0.73
     Habit
    -0.70
    ngdoc
    -0.70
    est
    -0.68
     ritual
    -0.68
    الحياه
    -0.66
    POSITIVE LOGITS
    uality
    0.62
    atic
    0.59
    uc
    0.57
    istic
    0.52
    timus
    0.51
    äu
    0.50
    ates
    0.49
     '{@
    0.49
    化した
    0.47
     Christendom
    0.47
    Activations Density 0.232%

    No Known Activations