© 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. 31865
    Prev
    Next
    INDEX
    Explanations

     nested list structures

    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
    MIDDLEWARE
    -0.65
    aarrggbb
    -0.62
    specifier
    -0.60
    WAUKEE
    -0.60
    RegressionTest
    -0.57
    UnusedPrivate
    -0.57
    ValueStyle
    -0.56
     المعيارى
    -0.55
    EndInit
    -0.54
    AddTagHelper
    -0.53
    POSITIVE LOGITS
     inggris
    0.64
    BAI
    0.58
    nelse
    0.56
     islas
    0.55
    feras
    0.55
     lunghe
    0.55
     mín
    0.54
     inglesa
    0.54
     SUNY
    0.54
     anglick
    0.54
    Activations Density 0.002%

    No Known Activations