© 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. 174
    Prev
    Next
    INDEX
    Explanations

    formal academic language and the structure of scientific papers, particularly sections that summarize findings and conclusions

    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
     Италијани
    -0.74
     Ehr
    -0.53
     nahilalakip
    -0.53
    RuleContext
    -0.51
     oprot
    -0.49
    iane
    -0.48
    RTLD
    -0.48
    Хьажоргаш
    -0.47
    Gambas
    -0.47
     mergeFrom
    -0.47
    POSITIVE LOGITS
     investigación
    0.50
     Forschung
    0.47
     purpoſe
    0.47
     HasFactory
    0.45
     onderzoek
    0.45
     Penelitian
    0.45
     research
    0.44
     penelitian
    0.43
     experimentally
    0.43
     propuesta
    0.43
    Activations Density 3.423%

    No Known Activations