© 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. 20-CLT-HP
    7. 78147
    Prev
    Next
    INDEX
    Explanations

    Various topics

    np_max-act-logits · 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
    Esperamos
    -0.49
     gọn
    -0.45
    mybatisplus
    -0.43
     vectorielle
    -0.42
     Praze
    -0.42
    hésite
    -0.41
     etik
    -0.41
     térmica
    -0.40
    hitung
    -0.39
     pageContext
    -0.39
    POSITIVE LOGITS
     issue
    0.75
     للمعارف
    0.74
    AxisAlignment
    0.71
     crowd
    0.70
     break
    0.69
     issues
    0.67
     succeed
    0.66
    twimg
    0.65
     spring
    0.65
     steal
    0.64
    Activations Density 0.000%

    No Known Activations