© 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. 1096
    Prev
    Next
    INDEX
    Explanations

    online sales offers, including phrases like "free shipping", "on orders", and amount thresholds marked with "$".

    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
     depic
    -0.55
     ویکی‌پدیا
    -0.54
    AlterField
    -0.54
     doubtnut
    -0.52
    تقاوى
    -0.51
     dumne
    -0.51
     незавершена
    -0.50
     Pseud
    -0.50
    aurais
    -0.50
     geslacht
    -0.48
    POSITIVE LOGITS
     discounts
    1.63
     discount
    1.63
     discounted
    1.57
     offer
    1.40
    discount
    1.29
     Offer
    1.29
     promo
    1.28
     Discounts
    1.26
     promotion
    1.26
     offers
    1.26
    Activations Density 0.766%

    No Known Activations