© 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. 24389
    Prev
    Next
    INDEX
    Explanations

    references to read/write operations related to data storage or processing

    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
     Stratton
    -0.64
    ation
    -0.61
     Others
    -0.61
     are
    -0.58
     protes
    -0.57
    Others
    -0.57
     is
    -0.57
    h
    -0.55
    “
    -0.54
    …
    -0.54
    POSITIVE LOGITS
     rw
    1.45
     RW
    1.38
    rw
    1.30
    RW
    1.29
     Rwand
    1.20
    Rwanda
    1.17
     Rwanda
    1.13
    setVerticalGroup
    1.10
     Kigali
    1.00
    Schneider
    0.97
    Activations Density 0.003%

    No Known Activations