© 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. 9308
    Prev
    Next
    INDEX
    Explanations

    instances of the word "few."

    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
    izations
    -0.74
    ladesh
    -0.72
     Portman
    -0.72
    RectangleBorder
    -0.71
    TintMode
    -0.69
    Berger
    -0.69
     Schuster
    -0.68
    aş
    -0.68
    לית
    -0.68
    اااا
    -0.67
    POSITIVE LOGITS
     few
    0.80
     Few
    0.77
     FEW
    0.77
     useRef
    0.73
     Huk
    0.71
    Few
    0.71
    XtraGrid
    0.68
     giu
    0.66
     pocos
    0.65
     wenige
    0.65
    Activations Density 0.028%

    No Known Activations