© 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. 15687
    Prev
    Next
    INDEX
    Explanations

    references to multi-chamber processes associated with electronics and medical applications

    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
     lenker
    -0.61
    dataTables
    -0.60
    riction
    -0.54
     فريبيس
    -0.54
     légale
    -0.53
     >=",
    -0.52
    RefNanny
    -0.51
     елның
    -0.50
     dipl
    -0.49
     CHAPITRE
    -0.49
    POSITIVE LOGITS
    OSSARY
    0.56
    arXiv
    0.54
    <?
    0.54
     Gogh
    0.52
    haya
    0.49
     BoxFit
    0.47
    Javascript
    0.46
    Климат
    0.46
    SharedDtor
    0.46
     Conversion
    0.45
    Activations Density 0.076%

    No Known Activations