Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 8417
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols related to integrals and differential equations

    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
    Rüyada
    -0.83
     JpaRepository
    -0.81
     nahilalakip
    -0.80
    tagHelperRunner
    -0.79
    Jeografia
    -0.76
    mybatisplus
    -0.75
     Infórmanos
    -0.74
     CreateTagHelper
    -0.72
     ویکی‌پدیا
    -0.72
     propOrder
    -0.71
    POSITIVE LOGITS
    กรรม
    0.49
    \_(
    0.46
    ‍
    0.40
     mancha
    0.40
     gesti
    0.40
    iget
    0.39
     censiti
    0.39
    ithe
    0.38
     مشين
    0.38
    LayoutPanel
    0.37
    Activations Density 0.065%

    No Known Activations