© 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. 1-RES-MATRYOSHKA-DC
    7. 1553
    Prev
    Next
    INDEX
    Explanations

    references to the word "odd" in various contexts

    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
    جغرافيا
    -0.58
     ajutor
    -0.57
    paksa
    -0.56
    letal
    -0.55
    Beskrivelse
    -0.55
     armées
    -0.54
    abinieri
    -0.54
    basics
    -0.53
    erçe
    -0.52
     krep
    -0.52
    POSITIVE LOGITS
     unusual
    3.05
     odd
    2.98
     strange
    2.78
    odd
    2.73
    unusual
    2.72
     Unusual
    2.69
     unique
    2.58
    Unusual
    2.56
    strange
    2.52
    Odd
    2.50
    Activations Density 0.474%

    No Known Activations