© 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. 2-RES-MATRYOSHKA-DC
    7. 3413
    Prev
    Next
    INDEX
    Explanations

    coefficients (parameters) used in a mathematical formula or computation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     alpha
    -0.82
     beta
    -0.79
    α
    -0.78
     α
    -0.76
     Beta
    -0.75
     Alpha
    -0.74
     epsilon
    -0.71
    Alpha
    -0.65
    psilon
    -0.63
    Beta
    -0.61
    POSITIVE LOGITS
    styleType
    0.94
    Personendaten
    0.88
     propOrder
    0.84
    Hentet
    0.80
    IntoConstraints
    0.80
     Vikipedi
    0.78
    MigrationBuilder
    0.77
     useAppContext
    0.77
     CreateTagHelper
    0.74
     ModelExpression
    0.74
    Activations Density 0.041%

    No Known Activations