© 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. 20728
    Prev
    Next
    INDEX
    Explanations

    medical terms related to treatments and biological therapies

    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
     Ceylon
    -0.66
     prisonniers
    -0.60
     Malaya
    -0.59
     cœurs
    -0.59
     citoyens
    -0.56
    ommen
    -0.55
     domésticos
    -0.55
     Aceh
    -0.55
     investissements
    -0.54
     Trix
    -0.53
    POSITIVE LOGITS
    imab
    1.37
    umab
    1.16
    XmlRootElement
    0.75
     VIAF
    0.72
    latego
    0.63
     Cytometry
    0.63
    alanta
    0.61
     Botox
    0.60
    oplasty
    0.58
    makedirs
    0.57
    Activations Density 0.013%

    No Known Activations