© 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. 22792
    Prev
    Next
    INDEX
    Explanations

    references to specific locations in a document, particularly referencing the top and bottom areas

    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
    ChromeDriver
    -0.74
     Channing
    -0.69
    twimg
    -0.64
    DeleteMapping
    -0.63
    ckså
    -0.61
     برانيه
    -0.61
     BeautifulSoup
    -0.60
    LikeLike
    -0.60
    BoxShadow
    -0.60
     mauva
    -0.58
    POSITIVE LOGITS
    Искәрмәләр
    0.56
    Rum
    0.51
    Vidite
    0.51
     دیکھیے
    0.46
    mère
    0.45
     mode
    0.45
    стного
    0.45
    stdc
    0.44
    rum
    0.44
    клопе
    0.43
    Activations Density 0.036%

    No Known Activations