© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 805
    Prev
    Next
    INDEX
    Explanations

    words and phrases involved in legal or technical reasoning, particularly when establishing relationships or dependencies.

    oai_token-act-pair · gemini-2.0-flash
    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
     Collection
    -0.48
     Ч
    -0.46
    +#+#
    -0.46
    ;
    -0.45
    렉
    -0.44
     Einsch
    -0.44
    ha
    -0.43
    ly
    -0.43
     Short
    -0.43
    Collection
    -0.42
    POSITIVE LOGITS
    RectangleBorder
    0.90
    ^(@)
    0.90
    באנגלית
    0.87
    onAttach
    0.87
     odkazy
    0.85
    limia
    0.80
    +:+
    0.79
     BoxDecoration
    0.76
     myſelf
    0.75
    ametros
    0.74
    Activations Density 2.851%

    No Known Activations