© 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. 2-RES-MATRYOSHKA-DC
    7. 5497
    Prev
    Next
    INDEX
    Explanations

    references to magnetic fields or the term "ub" associated with magnetic or electromagnetic concepts

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    MemoryWarning
    -0.65
    enumi
    -0.63
     viewType
    -0.63
     تانيه
    -0.62
    enumii
    -0.62
    HomeAsUpEnabled
    -0.58
     propOrder
    -0.57
     McGu
    -0.56
     Guthrie
    -0.54
    andowski
    -0.53
    POSITIVE LOGITS
    ub
    3.64
    UB
    2.64
    ubs
    2.05
     ub
    1.63
    ubi
    1.54
    ubb
    1.48
    uby
    1.48
    UBL
    1.47
    ubin
    1.44
     UB
    1.41
    Activations Density 0.006%

    No Known Activations