© 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. 0-CLT-HP
    7. 94500
    Prev
    Next
    INDEX
    Explanations

    Asking for opinions

    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
    -1.54
    think
    -1.10
    Think
    -0.99
     thinks
    -0.93
     Think
    -0.91
     thinking
    -0.79
     thought
    -0.76
     thinker
    -0.73
    rungsseite
    -0.71
     THINK
    -0.71
    POSITIVE LOGITS
    engeti
    0.58
     possible
    0.55
    )}_
    0.53
     the
    0.50
     potential
    0.49
    potential
    0.49
    addCriterion
    0.49
     eventuali
    0.48
     himo
    0.48
     '').
    0.47
    Activations Density 0.086%

    No Known Activations