© 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. 22-RES-MATRYOSHKA-DC
    7. 2665
    Prev
    Next
    INDEX
    Explanations

    numbers, especially years, and is also slightly activated by words like "assigned" or "application."

    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
    IntoConstraints
    -0.86
     Commencez
    -0.68
    RectangleBorder
    -0.66
    AutoresizingMask
    -0.63
    MeasureSpec
    -0.59
    webElementXpaths
    -0.59
    IUrlHelper
    -0.58
     EconPapers
    -0.56
     AspNetCore
    -0.55
     estimés
    -0.55
    POSITIVE LOGITS
     issued
    0.69
     issuance
    0.68
     entitled
    0.64
    出版年
    0.63
    issued
    0.61
     titled
    0.59
     issuing
    0.56
    entitled
    0.56
     Issued
    0.55
    Issued
    0.55
    Activations Density 0.058%

    No Known Activations