© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1227
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially last names, and also finds computer-related terms and chemistry terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Composable
    -0.91
    betic
    -0.86
     AXIS
    -0.85
    Kaynakça
    -0.84
     Satt
    -0.78
     Dutton
    -0.77
    InlineData
    -0.76
     Guin
    -0.75
    setParameter
    -0.75
    Armand
    -0.75
    POSITIVE LOGITS
     Beyer
    0.73
     Dew
    0.71
     Soto
    0.70
     McIntyre
    0.68
     mansions
    0.68
    NOUN
    0.67
     pert
    0.67
     Surrey
    0.66
    Dew
    0.66
    nextProps
    0.66
    Activations Density 4.556%

    No Known Activations