© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10473
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation related to functions and their properties

    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
    Negative Logits
    تقاوى
    -0.54
    shortcode
    -0.49
    IContainer
    -0.45
     phù
    -0.44
    ollection
    -0.44
    EditorBrowsable
    -0.43
     distanciation
    -0.42
    COLLE
    -0.42
     doanh
    -0.42
    ={({
    -0.42
    POSITIVE LOGITS
     nakalista
    0.72
    ngdoc
    0.71
    awaiter
    0.70
    setupUi
    0.69
    Personendaten
    0.66
     CommonModule
    0.64
     समीक्षाओं
    0.63
     betweenstory
    0.61
    RoutingModule
    0.60
    </em>
    0.59
    Activations Density 0.043%

    No Known Activations