© 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. 0-RES-MATRYOSHKA-DC
    7. 11111
    Prev
    Next
    INDEX
    Explanations

    references to dealing with capacity or nuance in discussions or analysis

    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
     CreateTagHelper
    -1.05
     examples
    -0.98
    Examples
    -0.97
     Examples
    -0.96
    Portail
    -0.96
    examples
    -0.93
     Beispiele
    -0.91
     EXAMPLES
    -0.90
    Diwedd
    -0.87
    enterOuterAlt
    -0.86
    POSITIVE LOGITS
    RESUMEN
    0.52
    RESUMO
    0.52
     Sequelize
    0.50
     Geset
    0.50
     činnosti
    0.50
     perquè
    0.50
     ktorý
    0.49
     acquistare
    0.49
     chiesto
    0.48
     paesi
    0.48
    Activations Density 0.010%

    No Known Activations