© 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. 23333
    Prev
    Next
    INDEX
    Explanations

    terms related to the process of development or progression of conditions or diseases

    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
     côtes
    -0.66
     hâte
    -0.65
     amélior
    -0.63
    makeConstraints
    -0.62
    odine
    -0.60
     manutenzione
    -0.60
     engraçadas
    -0.59
     gql
    -0.59
     suivie
    -0.58
     espoir
    -0.58
    POSITIVE LOGITS
    hood
    0.62
    principalTable
    0.62
     reag
    0.57
     AssemblyCulture
    0.57
    évaluateur
    0.57
    Acrylic
    0.56
    };*/
    0.56
    gania
    0.55
    kegaard
    0.55
    UnusedPrivate
    0.54
    Activations Density 0.023%

    No Known Activations