© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 25694
    Prev
    Next
    INDEX
    Explanations

    references to "bundles" in various 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
    Not in Any Lists

    No Comments

    Negative Logits
     Gough
    -0.91
    httphttps
    -0.85
     Starling
    -0.81
    BeginContext
    -0.81
    gasus
    -0.77
     marito
    -0.77
     IgA
    -0.75
    Perio
    -0.75
     lips
    -0.73
     Tại
    -0.72
    POSITIVE LOGITS
    Bundle
    1.59
     bundle
    1.48
     Bundle
    1.48
    bundle
    1.37
     bundles
    1.30
    bundles
    1.28
    UNDLE
    1.25
    Bundles
    1.22
     Bund
    1.04
    undle
    0.90
    Activations Density 0.008%

    No Known Activations