© 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. 32517
    Prev
    Next
    INDEX
    Explanations

    references to authors or researchers in scientific literature

    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
    AnchorStyles
    -0.80
    曖昧さ回避
    -0.65
    ResumeLayout
    -0.64
     together
    -0.63
    mergeFrom
    -0.60
     ResponseEntity
    -0.60
    tagHelperRunner
    -0.58
    together
    -0.56
     Wikispecies
    -0.56
     ویکی‌پدیای
    -0.54
    POSITIVE LOGITS
    >>;
    0.55
     prejudiced
    0.54
    nani
    0.53
    MeasureSpec
    0.51
    AFE
    0.51
    ahue
    0.47
    Dislikes
    0.47
     propOrder
    0.47
     Busse
    0.47
     paradas
    0.47
    Activations Density 0.019%

    No Known Activations