© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1912
    Prev
    Next
    INDEX
    Explanations

    words that could be names of people, places, or things, and technical or scientific terms, with preference for infection/immunity related

    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
     Kyrgyz
    -0.88
     Divinity
    -0.88
     Coulter
    -0.87
     Davido
    -0.86
     tamar
    -0.86
     Lorentz
    -0.84
     Paredes
    -0.84
    Zeneca
    -0.83
     Rosalind
    -0.83
     تضيفلها
    -0.83
    POSITIVE LOGITS
     Carney
    0.83
    ymce
    0.83
     Warren
    0.71
     vac
    0.68
     fee
    0.67
    moons
    0.64
    endregion
    0.63
    olstein
    0.63
    Warren
    0.63
    cer
    0.62
    Activations Density 4.418%

    No Known Activations