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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14892
    Prev
    Next
    INDEX
    Explanations

    references to organizations or entities involved in reporting or oversight activities

    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
    +#+#
    -1.11
    GraphicsUnit
    -0.88
    CodedInputStream
    -0.83
     propOrder
    -0.79
     الرياضيه
    -0.79
     >=",
    -0.77
    TintMode
    -0.77
    Gambas
    -0.75
     Roskov
    -0.74
    出版年
    -0.73
    POSITIVE LOGITS
     Independent
    1.48
    Independent
    1.19
     INDEPENDENT
    0.82
     Indep
    0.78
     Independiente
    0.69
     independ
    0.63
    independent
    0.57
     Independ
    0.56
     indépendante
    0.54
    </em>
    0.54
    Activations Density 0.010%

    No Known Activations