© 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. 20068
    Prev
    Next
    INDEX
    Explanations

    keywords related to solutions or proposed fixes

    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
     faſt
    -0.75
    Espèce
    -0.73
     Jove
    -0.73
     Elen
    -0.73
    AccessFile
    -0.71
     Kaspar
    -0.71
     незавершена
    -0.71
    ftagPool
    -0.69
     ་་
    -0.69
    Javadoc
    -0.68
    POSITIVE LOGITS
     solutions
    0.68
    Solution
    0.62
    Solutions
    0.61
     springfox
    0.60
    aarrggbb
    0.60
     Solutions
    0.59
    UTIONS
    0.57
     Solution
    0.57
    solutions
    0.57
    blon
    0.57
    Activations Density 0.007%

    No Known Activations