© 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. 10401
    Prev
    Next
    INDEX
    Explanations

    the keyword "defer"

    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
    Демографія
    -0.85
     estekak
    -0.85
     disambiguazione
    -0.77
    Földrajzportál
    -0.74
    verwijspagina
    -0.72
     viewDidLoad
    -0.69
    parsedMessage
    -0.69
    Réalisation
    -0.68
    milla
    -0.68
    Collegamenti
    -0.68
    POSITIVE LOGITS
    defer
    1.78
     defer
    0.96
    RectangleBorder
    0.58
    elseif
    0.57
    ailleurs
    0.54
    getOr
    0.52
    orElse
    0.50
    UMES
    0.50
    ili
    0.49
    ity
    0.48
    Activations Density 0.000%

    No Known Activations