© 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. 11704
    Prev
    Next
    INDEX
    Explanations

    references to subjects and study participants in a research context

    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
    AutoScale
    -0.92
    NameInMap
    -0.80
    TypedDataSet
    -0.80
    XmlAccessorType
    -0.78
    Personensuche
    -0.77
    StoryboardSegue
    -0.75
     >=",
    -0.73
    GEBURTSDATUM
    -0.73
    viewDidLoad
    -0.73
     Référence
    -0.72
    POSITIVE LOGITS
     properly
    0.58
     working
    0.54
     though
    0.54
     itself
    0.53
     simultaneously
    0.53
     too
    0.50
     throughout
    0.49
     rather
    0.48
     about
    0.48
     along
    0.46
    Activations Density 0.033%

    No Known Activations