© 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. 3164
    Prev
    Next
    INDEX
    Explanations

    the letters "PR" followed immediately by another letter

    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
    UMNS
    -0.69
    IDATE
    -0.60
    ایش
    -0.57
    ultar
    -0.56
     transférez
    -0.52
     Stif
    -0.52
     propon
    -0.52
    TintMode
    -0.52
    WithIOException
    -0.51
     >=",
    -0.49
    POSITIVE LOGITS
     pronouns
    0.54
     estrategias
    0.49
     nationaux
    0.49
     demurrer
    0.49
     voorwaarden
    0.48
    oplayer
    0.48
    er
    0.48
     schooner
    0.47
     printers
    0.47
    حوالہ
    0.46
    Activations Density 0.035%

    No Known Activations