© 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. 6145
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     has
    -0.53
     was
    -0.50
     متعلقه
    -0.50
     should
    -0.49
     can
    -0.48
     समीक्षाएं
    -0.48
     is
    -0.47
     dasarnya
    -0.45
     both
    -0.45
     also
    -0.45
    POSITIVE LOGITS
     parades
    0.63
     dinners
    0.60
     burials
    0.59
     bridesmaid
    0.58
    Vidite
    0.57
     hitters
    0.57
     Adair
    0.57
     parade
    0.57
     employes
    0.56
     mansions
    0.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.