© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1016
    Prev
    Next
    INDEX
    Explanations

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     think
    -1.46
     thinks
    -1.13
     thought
    -1.09
     Think
    -0.98
     pikir
    -0.91
     THINK
    -0.88
     thinking
    -0.86
     denken
    -0.81
    Think
    -0.81
    ihnachten
    -0.81
    POSITIVE LOGITS
    full
    0.76
    ings
    0.75
    -
    0.72
     to
    0.66
    work
    0.64
    cast
    0.64
    form
    0.63
    live
    0.61
    piece
    0.61
    file
    0.61
    Activations Density 0.015%

    No Known Activations