© 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. 27121
    Prev
    Next
    INDEX
    Explanations

    mentions of dependencies in a programming or technical context

    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
     überlegen
    -0.88
     Arad
    -0.84
     snippetHide
    -0.79
     Marl
    -0.78
     disambiguazione
    -0.77
    mels
    -0.75
     Gelb
    -0.75
     QM
    -0.73
     loisirs
    -0.71
    resultCode
    -0.71
    POSITIVE LOGITS
     dependency
    1.05
     dependencies
    0.97
     Dependency
    0.93
     Dependencies
    0.90
    dependency
    0.81
    Dependencies
    0.79
    Dependency
    0.77
    dependencies
    0.75
     الحره
    0.67
    mmä
    0.64
    Activations Density 0.003%

    No Known Activations