© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4197
    Prev
    Next
    INDEX
    Explanations

    mathematical set operation terms, particularly those related to intersections and unions

    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
     setuptools
    -0.60
    Typo
    -0.58
    utura
    -0.57
     Poste
    -0.57
     valour
    -0.57
     behind
    -0.56
     следует
    -0.56
     Yadav
    -0.55
     للمعارف
    -0.54
    payer
    -0.54
    POSITIVE LOGITS
    cap
    1.13
    ∩
    1.08
     cap
    0.97
    Cap
    0.90
     Cap
    0.86
     caps
    0.86
     Caps
    0.80
    CAP
    0.74
     Capp
    0.73
     Capri
    0.71
    Activations Density 0.022%

    No Known Activations