© 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. 13309
    Prev
    Next
    INDEX
    Explanations

    functions or skills related to measurement, precision, or enhancing capabilities

    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
     BoxDecoration
    -0.78
    RectangleBorder
    -0.77
     arşivlendi
    -0.75
    IntoConstraints
    -0.75
    RuleContext
    -0.74
    PreferredItem
    -0.74
     noqa
    -0.69
    LayoutConstraint
    -0.69
    جغرافيا
    -0.68
     ExecuteAsync
    -0.68
    POSITIVE LOGITS
    izes
    2.33
    IZES
    0.93
    ises
    0.65
    ates
    0.53
     experience
    0.50
    ]")]
    0.45
    oa̍t
    0.45
     نظ
    0.44
    不出
    0.43
    ευ
    0.42
    Activations Density 0.002%

    No Known Activations