© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 5646
    Prev
    Next
    INDEX
    Explanations

    elements of structured data presentation, particularly tables and their formatting

    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
    JspWriter
    -0.69
    DoubleQuotes
    -0.57
    pyplot
    -0.52
     Clément
    -0.52
    styleable
    -0.51
    PropertyChanged
    -0.51
    ;"></
    -0.51
     bross
    -0.50
    HtmlAttribute
    -0.49
     JFrame
    -0.49
    POSITIVE LOGITS
    Portale
    0.74
    AnchorStyles
    0.64
     ويكيپيديا
    0.58
    NUMX
    0.57
     copro
    0.56
    بوابة
    0.55
    omock
    0.54
     estimés
    0.52
     XNUMX
    0.52
     replays
    0.52
    Activations Density 0.051%

    No Known Activations