© 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. 32606
    Prev
    Next
    INDEX
    Explanations

    structure and formatting in technical or academic documents

    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
    oredCriteria
    -0.48
    elf
    -0.43
     dentelle
    -0.42
    pur
    -0.41
     establecimiento
    -0.40
     oras
    -0.40
    azz
    -0.39
    Share
    -0.38
    aaral
    -0.38
    Percy
    -0.37
    POSITIVE LOGITS
    AnchorStyles
    0.84
    enumi
    0.82
     getItemCount
    0.81
     doInBackground
    0.79
     CreateTagHelper
    0.75
    yship
    0.75
    XmlAccessorType
    0.75
    extAlignment
    0.75
    BufferException
    0.73
    FOOTNOTES
    0.73
    Activations Density 0.048%

    No Known Activations