© 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. 32478
    Prev
    Next
    INDEX
    Explanations

    notable occurrences or significant events in a timeline or narrative

    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
     समीक्षाओं
    -0.85
    AndEndTag
    -0.74
     USO
    -0.54
     distanciation
    -0.53
     FRP
    -0.52
     Lancelot
    -0.52
     Canad
    -0.52
     Suzy
    -0.51
     Aphrodite
    -0.50
    addComponent
    -0.49
    POSITIVE LOGITS
     AssemblyCulture
    0.73
     Roskov
    0.65
    Filmographie
    0.64
    slidesToShow
    0.61
    awaiter
    0.58
    MIDDLEWARE
    0.57
    RTHOOK
    0.56
    SequentialGroup
    0.56
    Retrieved
    0.55
     past
    0.54
    Activations Density 0.143%

    No Known Activations