© 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. 6000
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions or diagnoses involving the pancreas and respiratory system

    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
     CreateTagHelper
    -0.75
    makeConstraints
    -0.67
     transfieras
    -0.60
    writeFieldEnd
    -0.59
    +#+#
    -0.57
    ","");
    -0.56
    المناصب
    -0.54
     arşivlendi
    -0.54
    expandindo
    -0.53
     -}
    -0.52
    POSITIVE LOGITS
     usually
    0.78
     Usually
    0.75
    usually
    0.69
    Usually
    0.67
     solito
    0.59
     Typically
    0.57
     normalerweise
    0.57
     обычно
    0.56
     typically
    0.55
     trekken
    0.55
    Activations Density 0.348%

    No Known Activations