© 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. 14855
    Prev
    Next
    INDEX
    Explanations

    instances of physical interactions or processes

    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
    帖最后由
    -0.81
    localctx
    -0.66
    principalColumn
    -0.61
     CoreData
    -0.58
    RTSC
    -0.57
     propOrder
    -0.57
     overheating
    -0.56
    Cyfeiriadau
    -0.55
     vectorstock
    -0.55
    PreferredItem
    -0.55
    POSITIVE LOGITS
    XmlAccessType
    0.62
    mainAxisSize
    0.50
    RenderAtEndOf
    0.48
     danse
    0.44
     vốn
    0.44
    mapStateToProps
    0.44
     phénomène
    0.44
     Nauk
    0.44
    setVerticalGroup
    0.44
     ihop
    0.43
    Activations Density 0.477%

    No Known Activations