© 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. 95773
    Prev
    Next
    INDEX
    Explanations

    strong emotions

    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
     emotional
    -1.09
     emotionally
    -1.09
     Emotional
    -1.07
     emotion
    -1.04
    Emotional
    -1.04
     Emotion
    -1.03
    emotional
    -1.00
    Emotion
    -0.99
     wept
    -0.97
    emotion
    -0.93
    POSITIVE LOGITS
    ized
    0.68
    izing
    0.59
    ization
    0.58
    isé
    0.57
    ize
    0.52
    ike
    0.52
    ITY
    0.49
    iado
    0.47
     living
    0.46
    ise
    0.44
    Activations Density 0.171%

    No Known Activations