© 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. 6197
    Prev
    Next
    INDEX
    Explanations

    instances of structured data or formatted elements in a document

    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
    brainly
    -0.68
    :✨
    -0.57
    Personendaten
    -0.57
    toHaveBeen
    -0.49
     Normdatei
    -0.48
    aktor
    -0.48
     Rho
    -0.48
    ayak
    -0.45
     Biôgrafia
    -0.45
     decayed
    -0.45
    POSITIVE LOGITS
     Efq
    0.73
     alluminio
    0.66
    ſelf
    0.61
     pantaloni
    0.61
    antMatchers
    0.60
     doubtnut
    0.60
     invokingState
    0.60
     transfieras
    0.60
    Тогда
    0.60
     informée
    0.60
    Activations Density 0.005%

    No Known Activations