© 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. 20507
    Prev
    Next
    INDEX
    Explanations

    UI elements and their configurations in the context of coding and JSON structures

    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
    chooser
    -0.56
     comigo
    -0.55
    Rüyada
    -0.51
     invertible
    -0.51
     périph
    -0.48
    styleType
    -0.47
     térm
    -0.47
     ruota
    -0.46
     hiér
    -0.46
     profondità
    -0.46
    POSITIVE LOGITS
    BagConstraints
    0.70
     թվական
    0.68
     tématu
    0.66
    AnchorStyles
    0.58
     pinulongan
    0.58
    SharedDtor
    0.58
    djangoproject
    0.57
     ComVisible
    0.57
    RegistryLite
    0.57
    vician
    0.57
    Activations Density 0.011%

    No Known Activations