© 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. 11568
    Prev
    Next
    INDEX
    Explanations

    terms related to sports, particularly in the context of Olympic events and associated athletes

    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
    GHIJKLM
    -0.64
    ItemBackground
    -0.64
    tagHelperRunner
    -0.61
    ToScroll
    -0.59
    @[+][
    -0.59
     crackers
    -0.58
     transvers
    -0.57
     /\.
    -0.57
    EndInit
    -0.57
    ειν
    -0.57
    POSITIVE LOGITS
    __':
    0.76
    __':
    0.75
    __":
    0.65
    ```
    0.63
    calipsis
    0.57
    __":
    0.55
    umbai
    0.52
    stasy
    0.46
    ViewChild
    0.46
    mphony
    0.46
    Activations Density 0.011%

    No Known Activations