© 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. 26825
    Prev
    Next
    INDEX
    Explanations

    references to patches in various contexts, particularly in relation to fabric or clothing

    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
     propOrder
    -0.91
    PreInfinity
    -0.87
    httphttps
    -0.85
    ModelAdmin
    -0.82
    ToolStripButton
    -0.82
    קישורים
    -0.81
    DockStyle
    -0.80
     AssemblyCulture
    -0.78
     GenerationType
    -0.78
    AsUp
    -0.77
    POSITIVE LOGITS
     patches
    1.80
     patch
    1.73
     Patches
    1.66
     Patch
    1.64
    Patches
    1.57
    Patch
    1.55
    patch
    1.51
    patches
    1.50
     PATCH
    1.50
     patching
    1.27
    Activations Density 0.004%

    No Known Activations