© 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. 25361
    Prev
    Next
    INDEX
    Explanations

    patterns related to medical test results or diagnosis categories

    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
    Negative Logits
     Anſ
    -1.04
     purpoſe
    -1.02
     Reſ
    -1.02
     Houſe
    -0.98
     Eſ
    -0.95
     ſeveral
    -0.94
     auffi
    -0.93
     Inſ
    -0.92
     neceſſ
    -0.92
     Jefus
    -0.91
    POSITIVE LOGITS
    ojo
    0.59
     mis
    0.54
    PINES
    0.52
     “
    0.51
    ruptedException
    0.50
    \
    0.49
     Pro
    0.47
     ‘
    0.47
    ”
    0.47
    راب
    0.47
    Activations Density 0.040%

    No Known Activations