© 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. 20332
    Prev
    Next
    INDEX
    Explanations

    words related to specific medical conditions or treatments

    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
    indro
    -0.64
    gyz
    -0.63
     Svet
    -0.60
     maig
    -0.60
     donor
    -0.60
    playa
    -0.60
     donate
    -0.59
    gast
    -0.57
     gavetas
    -0.57
    vania
    -0.56
    POSITIVE LOGITS
     amyloid
    0.89
    stateProvider
    0.68
    HttpGet
    0.60
    loid
    0.58
    Lenny
    0.57
    MENAFN
    0.57
     Schal
    0.56
    addContainerGap
    0.52
    oredCriteria
    0.50
     specchio
    0.50
    Activations Density 0.001%

    No Known Activations