© 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. 14482
    Prev
    Next
    INDEX
    Explanations

    phrases related to patient outcomes in medical studies

    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
    tela
    -0.49
     causing
    -0.46
    "./
    -0.45
     pros
    -0.44
     Ne
    -0.43
     Cate
    -0.43
    TST
    -0.42
     see
    -0.42
    াব
    -0.41
    ="?
    -0.41
    POSITIVE LOGITS
     springfox
    0.91
    GraphicsUnit
    0.90
     saites
    0.90
     cherchés
    0.90
     betweenstory
    0.87
    +#+#
    0.87
    AndroidJUnit
    0.84
    kháu
    0.84
    featureID
    0.79
     <<<<<<<<<<<<<<
    0.79
    Activations Density 0.088%

    No Known Activations