© 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. 28856
    Prev
    Next
    INDEX
    Explanations

    medical terminology and phrases related to cardiac health and outcomes

    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
     ferons
    -0.53
     rosas
    -0.50
     widok
    -0.47
     masiva
    -0.45
     heading
    -0.44
     испо
    -0.43
    Heading
    -0.43
    heading
    -0.42
     vnode
    -0.42
     Map
    -0.41
    POSITIVE LOGITS
    LookAnd
    0.85
    Datuak
    0.76
    ImageContext
    0.74
     CreateTagHelper
    0.70
    IntoConstraints
    0.69
    GraphicsUnit
    0.66
     "..\..\
    0.66
     autorytatywna
    0.63
    URLException
    0.62
    зулта
    0.60
    Activations Density 0.330%

    No Known Activations