© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 637
    Prev
    Next
    INDEX
    Explanations

    reviews and opinions about books, including mentions of authors, book titles, and related terminology like "ebook", "paper edition", "hardcover" and "YA/Teen Book Club".

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.76
    Hozzáférés
    -0.69
     Exacts
    -0.67
     protoimpl
    -0.67
    Datuak
    -0.66
     SIMBAD
    -0.62
     HasFactory
    -0.62
    
    -0.61
    stateProvider
    -0.60
     مرئيه
    -0.59
    POSITIVE LOGITS
     book
    1.52
     books
    1.46
     author
    1.30
     novels
    1.26
     authors
    1.26
     Book
    1.24
    books
    1.21
     Books
    1.20
     paperback
    1.20
    book
    1.19
    Activations Density 1.510%

    No Known Activations