© 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. 18831
    Prev
    Next
    INDEX
    Explanations

    structured data elements and key-value pairs in programming code

    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
    orianCalendar
    -0.57
    athies
    -0.53
     зако
    -0.50
    −/−
    -0.47
     становника
    -0.46
    hala
    -0.45
     Bacteriol
    -0.45
     Said
    -0.43
     común
    -0.43
     Estadística
    -0.42
    POSITIVE LOGITS
    AddTagHelper
    0.75
     EconPapers
    0.69
    Jereo
    0.68
    NameInMap
    0.67
     autorytatywna
    0.65
    GenerationType
    0.62
     للمعارف
    0.61
     noDo
    0.59
    EndProject
    0.58
     jspb
    0.57
    Activations Density 0.019%

    No Known Activations