© 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. 15732
    Prev
    Next
    INDEX
    Explanations

    references to specific groups or categories within structured contexts

    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
     AssemblyTitle
    -0.79
     esternos
    -0.74
    LookAnd
    -0.73
     Italij
    -0.72
     InputDecoration
    -0.72
     ویکی‌پدی
    -0.71
    lgari
    -0.70
     uska
    -0.69
    Jeografia
    -0.69
    ⓧ
    -0.68
    POSITIVE LOGITS
     sinh
    0.47
     disambiguazione
    0.46
     Hospital
    0.45
     Dios
    0.45
     …
    0.43
     Document
    0.42
    ResponseCode
    0.42
     documenta
    0.41
    Dieu
    0.41
    стори
    0.41
    Activations Density 0.215%

    No Known Activations