© 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. 10692
    Prev
    Next
    INDEX
    Explanations

    instances of the "begin" and "end" commands in a document structure

    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
    usepackage
    -0.68
    oule
    -0.51
    verwijspagina
    -0.51
     وتسجيلات
    -0.47
     ujednoznacz
    -0.47
     <<<<<<<<<<<<<<
    -0.43
     المعيارى
    -0.43
    readString
    -0.43
    gpg
    -0.43
     VERSITY
    -0.43
    POSITIVE LOGITS
    RegistryLite
    0.74
     AssemblyTitle
    0.73
    UIControlState
    0.61
    RenderAtEndOf
    0.60
    TypedDataSet
    0.59
    ilstein
    0.59
     _$
    0.59
    例句
    0.59
     WaitForSeconds
    0.58
    AlterField
    0.58
    Activations Density 0.001%

    No Known Activations