© 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-RES-MATRYOSHKA-DC
    7. 10652
    Prev
    Next
    INDEX
    Explanations

    references to scientific experiments and related methodological descriptions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    })*/
    -0.62
    ंदीखरीदारी
    -0.60
     bewe
    -0.56
    AndEndTag
    -0.54
    Viitteet
    -0.53
    Comté
    -0.52
     CONCLUSION
    -0.52
    Acknowledgment
    -0.52
    aragus
    -0.51
    Portale
    -0.50
    POSITIVE LOGITS
    Results
    1.62
    RESULTS
    1.35
     Results
    1.14
     RESULTS
    0.88
    tagHelperRunner
    0.87
     Resultados
    0.87
    Resultados
    0.77
     Rates
    0.77
    Résultats
    0.72
    RESULTADOS
    0.71
    Activations Density 0.005%

    No Known Activations