© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14814
    Prev
    Next
    INDEX
    Explanations

    explanations involving technical or scientific discussions

    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
    +#+#
    -0.72
     Puis
    -0.62
    MLLoader
    -0.61
    ItemBackground
    -0.61
    Puis
    -0.60
    anzia
    -0.59
    发表于
    -0.59
     Socialista
    -0.57
     بيها
    -0.57
     varandra
    -0.57
    POSITIVE LOGITS
     Apart
    1.98
     Aside
    1.93
    Aside
    1.91
    Apart
    1.79
    apart
    0.85
    apimachinery
    0.73
    RenderAtEndOf
    0.69
    ConstraintMaker
    0.67
    Along
    0.60
    Alongside
    0.59
    Activations Density 0.002%

    No Known Activations