© 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. 25814
    Prev
    Next
    INDEX
    Explanations

    structured data format indicators, particularly related to programming objects or arrays

    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
     Redondo
    -0.62
    odeon
    -0.61
    /−
    -0.60
     möjlighet
    -0.59
     MMM
    -0.57
     McDonough
    -0.57
    OVO
    -0.54
     Iman
    -0.54
     reprodução
    -0.52
    erráneo
    -0.52
    POSITIVE LOGITS
    @{
    2.06
     @{
    1.63
    Lähteet
    0.96
     Lea
    0.65
    ..\..\
    0.64
     swift
    0.62
    Искәрмәләр
    0.62
    ={({
    0.61
    Lea
    0.61
     Sala
    0.60
    Activations Density 0.002%

    No Known Activations