© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8646
    Prev
    Next
    INDEX
    Explanations

    text related to web development and programming elements, particularly focusing on HTML layout and styling components

    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
    はじめに
    -0.69
    titleMargin
    -0.66
     ostavi
    -0.62
     gawas
    -0.62
    XtraEditors
    -0.60
     pinulongan
    -0.57
    uestamente
    -0.57
    ronpa
    -0.56
     simplifié
    -0.56
    жнему
    -0.56
    POSITIVE LOGITS
     arşivlendi
    0.59
    SpringBootTest
    0.58
    didSet
    0.57
    consulté
    0.54
    DockStyle
    0.51
     BoxDecoration
    0.50
    MemoryWarning
    0.50
    mergeFrom
    0.50
    URIComponent
    0.49
    jspx
    0.49
    Activations Density 0.062%

    No Known Activations