© 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. 13967
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations related to vector spaces and matrices

    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
    хьтан
    -0.79
     propOrder
    -0.77
     AssemblyVersion
    -0.76
    AndEndTag
    -0.72
     تانيه
    -0.71
    aarrggbb
    -0.68
    :✨
    -0.68
     وتسجيلات
    -0.67
    InjectAttribute
    -0.62
    PreferredItem
    -0.61
    POSITIVE LOGITS
     bezeichneter
    0.54
    PRNewswire
    0.50
    ])){
    0.49
    blik
    0.47
    .*")]
    0.46
     estimés
    0.44
    useEffect
    0.43
    __()
    0.43
     Gegenteil
    0.43
    IANGLES
    0.43
    Activations Density 0.038%

    No Known Activations