© 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. 22-RES-MATRYOSHKA-DC
    7. 3029
    Prev
    Next
    INDEX
    Explanations

    parenthetical statements and acronyms within scientific texts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ReusableCell
    -0.56
     समीक्षाओं
    -0.54
    ThemeOverlay
    -0.51
     Sully
    -0.49
     Barrie
    -0.49
     Scarlett
    -0.48
     nahilalakip
    -0.48
     calendriers
    -0.47
    爐
    -0.47
     Allen
    -0.46
    POSITIVE LOGITS
     BP
    1.40
     DP
    1.40
     CP
    1.37
     FP
    1.34
    BP
    1.34
     KP
    1.34
    DP
    1.34
     RP
    1.32
    RP
    1.31
    CP
    1.28
    Activations Density 1.271%

    No Known Activations