© 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. 3-RES-MATRYOSHKA-DC
    7. 2532
    Prev
    Next
    INDEX
    Explanations

    the word "think"

    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
     thinking
    -1.07
     Thought
    -1.02
     thought
    -0.97
     Thinking
    -0.97
    Thought
    -0.95
     THOUGHT
    -0.93
    thinking
    -0.92
    Thinking
    -0.87
     assumes
    -0.86
    thought
    -0.85
    POSITIVE LOGITS
    FailureListener
    0.77
    MigrationBuilder
    0.74
    parsedMessage
    0.68
    Xna
    0.68
     uVar
    0.67
    aarrggbb
    0.67
    ThroughAttribute
    0.66
    ///</
    0.65
    Chham
    0.62
     SPDX
    0.62
    Activations Density 0.063%

    No Known Activations