© 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. 9497
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific formatting elements in scientific or technical writing

    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
    GraphicsUnit
    -0.65
    BeginContext
    -0.59
    ContentAlignment
    -0.59
    ANTLR
    -0.57
    ("</
    -0.57
    –)
    -0.56
     استنادى
    -0.56
    +"&
    -0.55
    avao
    -0.55
    AnchorStyles
    -0.54
    POSITIVE LOGITS
    verwijspagina
    0.64
    Composable
    0.54
     تانيه
    0.49
     CURIAM
    0.48
    ArrowToggle
    0.48
    AndEndTag
    0.48
     Plague
    0.47
    PreAuthorize
    0.47
     Normdatei
    0.46
     AssemblyTitle
    0.46
    Activations Density 0.016%

    No Known Activations