© 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. 18-RES-MATRYOSHKA-DC
    7. 1375
    Prev
    Next
    INDEX
    Explanations

    the word "each"

    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.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     Italijanski
    -0.57
     SUT
    -0.56
     دیکھیے
    -0.56
    able
    -0.56
    Personensuche
    -0.54
     hotspots
    -0.54
    elts
    -0.52
    Klo
    -0.51
    /-
    -0.50
    rophes
    -0.50
    POSITIVE LOGITS
     einzelnen
    0.88
    enumi
    0.79
     individually
    0.77
    각
    0.77
     jednotliv
    0.73
     successive
    0.73
     eneste
    0.73
     separately
    0.73
     every
    0.71
    masing
    0.71
    Activations Density 0.136%

    No Known Activations