© 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. 18588
    Prev
    Next
    INDEX
    Explanations

    references to lists or definitions in a structured format

    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
     Garrick
    -0.81
     Shiva
    -0.76
    Shiva
    -0.75
     Salvador
    -0.75
     Kass
    -0.74
     Oakley
    -0.73
    casio
    -0.73
    meau
    -0.73
     Nixon
    -0.71
     Ernesto
    -0.71
    POSITIVE LOGITS
    DL
    1.27
    dl
    1.22
     DL
    1.20
     dl
    1.05
    Dl
    0.77
    KX
    0.71
    theless
    0.69
    Portale
    0.69
    ύν
    0.68
     Zinn
    0.66
    Activations Density 0.005%

    No Known Activations