© 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. 0-RES-MATRYOSHKA-DC
    7. 10468
    Prev
    Next
    INDEX
    Explanations

    mathematical or logical expressions related to statistical and scientific notation

    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
     comp
    -1.56
     COMP
    -1.02
     Compens
    -0.81
     complicate
    -0.79
    Comp
    -0.77
     Comp
    -0.75
     Compensation
    -0.73
     comps
    -0.71
    photobucket
    -0.71
     المعيارى
    -0.71
    POSITIVE LOGITS
    comp
    1.52
     complementary
    0.80
    complement
    0.79
     complement
    0.69
     comprende
    0.66
     comprising
    0.65
    Complement
    0.63
     comprises
    0.62
     complé
    0.61
     complements
    0.60
    Activations Density 0.001%

    No Known Activations