© 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. 1-CLT-HP
    7. 14356
    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
    -0.78
     Think
    -0.70
    Think
    -0.68
     thinking
    -0.59
     THINK
    -0.57
     thinks
    -0.55
     that
    -0.53
     expect
    -0.50
    think
    -0.50
    anskje
    -0.48
    POSITIVE LOGITS
    er
    0.84
    StoryboardSegue
    0.84
    MessageTagHelper
    0.81
     >=",
    0.79
    GraphicsUnit
    0.78
    ability
    0.78
    adaptiveStyles
    0.77
    eting
    0.77
    enumii
    0.77
    ness
    0.76
    Activations Density 0.003%

    No Known Activations