© 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. 15844
    Prev
    Next
    INDEX
    Explanations

    references to subgroups in research analyses

    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
     ComVisible
    -1.16
    GEBURTSDATUM
    -0.95
     Picchu
    -0.78
    DockStyle
    -0.78
    RunAsync
    -0.75
    клопе
    -0.74
    pery
    -0.72
    Busch
    -0.71
    )}</
    -0.71
    olescence
    -0.70
    POSITIVE LOGITS
     subgroups
    1.06
     subgroup
    1.00
    ing
    0.87
    UIControlState
    0.70
     reafon
    0.69
     deſt
    0.68
     Antioch
    0.68
     Bartol
    0.67
    HtmlAttribute
    0.66
     newNode
    0.66
    Activations Density 0.003%

    No Known Activations