© 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. 25491
    Prev
    Next
    INDEX
    Explanations

    phrases related to experimental methods and data presentation in research contexts

    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
     AssemblyCompany
    -0.57
    onOptions
    -0.57
    UseVisualStyle
    -0.56
    tieg
    -0.52
     AssemblyProduct
    -0.51
    HandlerContext
    -0.48
    ита
    -0.47
    isin
    -0.47
    San
    -0.46
     benches
    -0.46
    POSITIVE LOGITS
    +#+#
    0.77
    tagHelperRunner
    0.76
    IUrlHelper
    0.76
    MLLoader
    0.66
    fjspx
    0.60
    WithFormat
    0.59
     nemlig
    0.59
    ьаж
    0.59
    ViewFeatures
    0.58
    GEBURTSDATUM
    0.58
    Activations Density 0.016%

    No Known Activations