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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 697
    Prev
    Next
    INDEX
    Explanations

    references to web pages and their metadata

    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
    كويكب
    -0.69
     tiba
    -0.67
     ISNI
    -0.65
    AntiForgeryToken
    -0.62
    amazonaws
    -0.61
     Drit
    -0.60
    NameInMap
    -0.59
     Stout
    -0.59
     initView
    -0.59
    AndEndTag
    -0.58
    POSITIVE LOGITS
     page
    1.69
     pages
    1.65
     getPage
    1.64
     PAGE
    1.60
     Pages
    1.60
     Page
    1.55
    Pages
    1.52
    pages
    1.52
    PAGE
    1.49
     PAGES
    1.41
    Activations Density 0.194%

    No Known Activations