© 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. 10627
    Prev
    Next
    INDEX
    Explanations

    structured data outputs, particularly formatted symbols and mathematical notations

    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
    ⓧ
    -0.70
    InjectAttribute
    -0.59
    jstor
    -0.58
     <=",
    -0.58
    Vidite
    -0.57
     autorytatywna
    -0.52
     protoimpl
    -0.52
    pyplot
    -0.51
    Encyklopedia
    -0.51
    XmlAccessorType
    -0.51
    POSITIVE LOGITS
     للمعارف
    0.78
     الدولى
    0.59
    AndEndTag
    0.57
    bootstrapcdn
    0.55
     >=",
    0.54
     RoutedEventArgs
    0.53
    rancy
    0.52
    BufferException
    0.51
    TProtocol
    0.51
    çadas
    0.50
    Activations Density 0.372%

    No Known Activations