© 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. 2815
    Prev
    Next
    INDEX
    Explanations

    terms related to software package management and molecular biology

    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
     supervisors
    -0.57
     Prisoners
    -0.56
     superintendents
    -0.55
     boulders
    -0.54
     useAppContext
    -0.54
     Salmo
    -0.53
     salmon
    -0.53
     Morality
    -0.53
     anatom
    -0.52
    jaus
    -0.52
    POSITIVE LOGITS
    npmjs
    0.80
    yarnpkg
    0.79
     SqlDbType
    0.75
    QMetaType
    0.70
    apimachinery
    0.69
    odils
    0.68
    googleapis
    0.65
     SqlCommand
    0.62
    XMLSchema
    0.61
    makeText
    0.59
    Activations Density 1.208%

    No Known Activations