© 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. 95634
    Prev
    Next
    INDEX
    Explanations

    shine

    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
     bright
    -1.32
    bright
    -1.22
     brightest
    -1.22
    Bright
    -1.21
     brightness
    -1.20
     brilhante
    -1.19
     shining
    -1.16
     brighter
    -1.16
     brilho
    -1.16
     shine
    -1.13
    POSITIVE LOGITS
     fin
    0.48
    est
    0.47
     ce
    0.47
     enough
    0.47
     di
    0.47
     dia
    0.46
     cas
    0.46
     dag
    0.45
    y
    0.45
     fide
    0.45
    Activations Density 0.044%

    No Known Activations