© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17859
    Prev
    Next
    INDEX
    Explanations

    numerical references and structured citations in legal or formal documents

    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
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.80
     AssemblyProduct
    -0.65
     iconFacebook
    -0.65
     كومونز
    -0.62
     ویکی‌پدیا
    -0.62
    WriteBarrier
    -0.60
    اریخ
    -0.59
     EnglishChoose
    -0.59
    Glej
    -0.59
     absolue
    -0.59
    POSITIVE LOGITS
    NOPQRST
    0.47
    </thead>
    0.44
     Sti
    0.43
    DataAnnotations
    0.43
     Sal
    0.43
    Legenda
    0.42
    DoubleQuotes
    0.42
    ilever
    0.41
    suri
    0.41
    atrix
    0.41
    Activations Density 0.192%

    No Known Activations