© 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. 24-RES-MATRYOSHKA-DC
    7. 1614
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to books and/or reading

    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.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    Билгалдахарш
    -0.66
    تقاوى
    -0.65
     Exacts
    -0.64
    Datuak
    -0.63
    tanleria
    -0.63
     مرئيه
    -0.62
    ClientSize
    -0.61
     protoimpl
    -0.58
    apimachinery
    -0.57
     überweisen
    -0.57
    POSITIVE LOGITS
     books
    1.46
     book
    1.43
     novels
    1.29
     paperback
    1.21
     Books
    1.17
     novel
    1.16
     authors
    1.16
     author
    1.13
    books
    1.12
     Goodreads
    1.11
    Activations Density 1.322%

    No Known Activations