© 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. 2-RES-MATRYOSHKA-DC
    7. 7723
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions or health-related issues

    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
     Bài
    -0.59
    serviceWorker
    -0.57
    Motto
    -0.56
     monotonic
    -0.56
    PyExc
    -0.55
     myſelf
    -0.54
     amphi
    -0.53
     Lerner
    -0.53
    breos
    -0.53
     gamma
    -0.52
    POSITIVE LOGITS
     suspect
    3.14
     suspects
    2.80
    sus
    2.48
     suspected
    2.47
     suspicion
    2.45
     Sus
    2.41
    Sus
    2.28
     suspe
    2.23
     sospe
    2.17
     suspicions
    2.03
    Activations Density 0.043%

    No Known Activations