© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 325
    Prev
    Next
    INDEX
    Explanations

    words related to celebrations and cultural festivals

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     betweenstory
    -1.19
    parsedMessage
    -1.19
    IUrlHelper
    -1.15
     Италијани
    -1.13
    GEBURTSDATUM
    -1.09
     ویکی‌پدی
    -1.09
    <unused23>
    -1.06
    <unused28>
    -1.06
    <unused41>
    -1.06
    <unused43>
    -1.06
    POSITIVE LOGITS
     
    0.69
    s
    0.53
     \
    0.48
     the
    0.44
    \
    0.43
     $
    0.42
    0.42
    ↵
    0.40
    1
    0.40
      
    0.38
    Activations Density 20.195%
    No Known Activations