© 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. 12-RES-MATRYOSHKA-DC
    7. 15356
    Prev
    Next
    INDEX
    Explanations

    medical terms and concepts related to health outcomes and statistical analysis

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueGeneration
    -0.64
    twimg
    -0.64
    rzost
    -0.58
    scriptcase
    -0.57
     Paglinawan
    -0.49
     AssemblyCulture
    -0.48
    lapia
    -0.48
    ≦)
    -0.48
    Jereo
    -0.48
    webElementXpaths
    -0.47
    POSITIVE LOGITS
     disambiguazione
    0.67
    הערות
    0.60
     useStyles
    0.58
     Theſe
    0.57
    EndInit
    0.56
     myſelf
    0.56
     useDispatch
    0.55
     שוליים
    0.55
     againſt
    0.55
    tonsoft
    0.54
    Activations Density 0.008%

    No Known Activations