© 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. 30871
    Prev
    Next
    INDEX
    Explanations

    special formatting or separators in structured 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
    ⓧ
    -0.80
    PhysRev
    -0.73
     autorytatywna
    -0.69
    ISupport
    -0.68
    PRNewswire
    -0.68
     استنادى
    -0.68
    CreateMap
    -0.68
     Inscrivez
    -0.67
    principalTable
    -0.64
    NamedQueries
    -0.64
    POSITIVE LOGITS
    ndham
    0.47
     بيانات
    0.46
     documentation
    0.46
     ๆ
    0.45
    ordenadas
    0.45
     Laval
    0.45
    odenal
    0.44
    niska
    0.44
    yeti
    0.44
    rops
    0.44
    Activations Density 0.003%

    No Known Activations