© 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. 20450
    Prev
    Next
    INDEX
    Explanations

    attributes and parameters related to system components

    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
    <()>
    -1.02
     Roca
    -1.01
    Rolf
    -0.87
     Unies
    -0.85
     Canucks
    -0.85
    ’?
    -0.84
    =-=-=-=-
    -0.82
     Rolf
    -0.82
     newBuilder
    -0.80
     OMIT
    -0.79
    POSITIVE LOGITS
    1.20
     django
    0.78
    _^
    0.76
     UnityEngine
    0.75
    III
    0.75
    обла
    0.75
    GEO
    0.73
     Marjorie
    0.73
    rdida
    0.73
     GEO
    0.72
    Activations Density 0.100%

    No Known Activations