© 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. 3-RES-MATRYOSHKA-DC
    7. 3235
    Prev
    Next
    INDEX
    Explanations

    the word "cup" in recipes or math equations

    oai_token-act-pair · gemini-2.0-flash
    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
     Duane
    -0.67
    Duane
    -0.66
     marche
    -0.63
    ishna
    -0.61
     Burgos
    -0.60
    Filmo
    -0.59
    makeText
    -0.58
    JvmStatic
    -0.58
    mogorov
    -0.58
    //
    -0.57
    POSITIVE LOGITS
     cup
    3.34
     Cup
    3.23
    cup
    3.17
     cups
    2.98
    Cup
    2.98
     Cups
    2.89
     CUP
    2.75
    cups
    2.47
    CUP
    2.34
    カップ
    1.88
    Activations Density 0.021%

    No Known Activations