© 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. 10675
    Prev
    Next
    INDEX
    Explanations

    mathematical operations, specifically those involving the wedge product in linear algebra

    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
    Negative Logits
     Rosalind
    -0.85
     Rohit
    -0.81
     Rosal
    -0.80
    ſelf
    -0.79
     ſal
    -0.77
     Reſ
    -0.77
    eff
    -0.76
     Dili
    -0.76
     ricor
    -0.76
     eſſ
    -0.76
    POSITIVE LOGITS
    wedge
    1.31
     Wedge
    0.82
    ∧
    0.79
     wedge
    0.73
    URLException
    0.65
     Hedges
    0.63
     wedges
    0.58
    ]^
    0.58
    engaruhi
    0.57
    pch
    0.56
    Activations Density 0.003%

    No Known Activations