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. 23198
    Prev
    Next
    INDEX
    Explanations

    elements related to structure and formatting in a markup or programming context

    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
    addCriterion
    -0.41
    ötä
    -0.40
    oriya
    -0.40
    бя
    -0.40
     humaines
    -0.39
    تفصیلات
    -0.39
    tribune
    -0.39
    MathML
    -0.38
     OFDb
    -0.37
     naturali
    -0.36
    POSITIVE LOGITS
    دانشنامهٔ
    0.93
    ISupport
    0.93
     initComponents
    0.78
    HasForeignKey
    0.77
    تقاوى
    0.73
     EconPapers
    0.69
    RectangleBorder
    0.68
     odkazy
    0.68
    =$?
    0.67
    EndInit
    0.66
    Activations Density 0.419%

    No Known Activations