© 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. 5086
    Prev
    Next
    INDEX
    Explanations

    database schema elements, particularly related to table and field definitions

    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
    aarrggbb
    -0.74
     متعلقه
    -0.73
    IUrlHelper
    -0.73
    rrggbb
    -0.71
    AnimationFrame
    -0.69
     estekak
    -0.63
     للاسماء
    -0.63
    ագրություններ
    -0.62
    ChildScrollView
    -0.62
     xlink
    -0.60
    POSITIVE LOGITS
     Longer
    0.48
     betweenstory
    0.47
     maxLength
    0.45
     chars
    0.45
     longer
    0.44
    cured
    0.44
    chars
    0.43
    ئية
    0.43
     characters
    0.42
     oprot
    0.42
    Activations Density 0.141%

    No Known Activations