© 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. 20648
    Prev
    Next
    INDEX
    Explanations

    references to photographs and their descriptions

    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
    EnableWeb
    -0.65
     Cze
    -0.59
     Hedges
    -0.58
    Câu
    -0.55
    ])):
    -0.54
    Republic
    -0.52
    Altitude
    -0.52
     Republic
    -0.52
     apporté
    -0.50
     Harts
    -0.50
    POSITIVE LOGITS
    DockStyle
    1.07
     typelib
    0.84
    principalTable
    0.75
    webElementXpaths
    0.67
    principalColumn
    0.66
    
    0.66
    IUrlHelper
    0.65
    itect
    0.65
    UnusedPrivate
    0.64
    RSpec
    0.63
    Activations Density 0.081%

    No Known Activations