© 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. 793
    Prev
    Next
    INDEX
    Explanations

    variations of 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
    aderie
    -0.92
     Audiodateien
    -0.81
    ExecuteReader
    -0.71
     snippetHide
    -0.70
     aDecoder
    -0.70
    jooq
    -0.69
     Zas
    -0.68
     تضيفلها
    -0.67
     utafitiHapana
    -0.66
    ypep
    -0.65
    POSITIVE LOGITS
     think
    2.41
     THINK
    2.36
     Think
    2.31
    think
    2.28
    THINK
    2.27
    Think
    2.25
     thought
    2.17
     Thought
    2.16
     thinking
    2.14
     Thinking
    2.13
    Activations Density 0.093%

    No Known Activations