© 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. 6210
    Prev
    Next
    INDEX
    Explanations

    patterns of whitespace tokens in relation to structured data or code formatting

    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
    POSED
    -0.49
    wenden
    -0.46
    ec
    -0.46
    ph
    -0.45
     segment
    -0.45
    ovec
    -0.44
    posable
    -0.44
     Bu
    -0.43
    qu
    -0.43
     Pi
    -0.42
    POSITIVE LOGITS
    TagMode
    1.02
     lenker
    1.00
     ModelExpression
    0.90
    AddTagHelper
    0.89
    DoubleQuotes
    0.83
     CreateTagHelper
    0.82
     tartalomajánló
    0.81
    tagHelperRunner
    0.78
    HandlerContext
    0.77
    NameInMap
    0.76
    Activations Density 0.010%

    No Known Activations