© 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. 6290
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to pathology and disease

    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
     Sumer
    -0.85
     Sarm
    -0.82
     cune
    -0.78
     Zet
    -0.76
    CPtr
    -0.75
     Mers
    -0.73
     Mev
    -0.73
    mergeFrom
    -0.72
     Aza
    -0.72
     الاطلاع
    -0.71
    POSITIVE LOGITS
     Patho
    1.44
    patho
    1.34
    opatho
    1.19
    Patho
    1.19
     patho
    1.12
     PATH
    1.02
     pathogens
    1.00
     Pathology
    0.96
     Pathol
    0.94
     pathogen
    0.93
    Activations Density 0.063%

    No Known Activations