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. 215
    Prev
    Next
    INDEX
    Explanations

    key attributes in CSS styles and HTML structure

    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
     ویکی‌پدیا
    -1.06
    LookAnd
    -0.96
     المعيارى
    -0.96
     nahilalakip
    -0.94
    XmlEnum
    -0.89
    SourceChecksum
    -0.88
    WriteBarrier
    -0.86
     calendriers
    -0.85
    :✨
    -0.85
     kasarigan
    -0.85
    POSITIVE LOGITS
    AnchorStyles
    0.52
     important
    0.50
     
    0.44
     theme
    0.42
    extAlignment
    0.42
     font
    0.42
     scalable
    0.41
    лене
    0.41
     column
    0.41
     small
    0.40
    Activations Density 1.367%

    No Known Activations