© 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. 42625
    Prev
    Next
    INDEX
    Explanations

    excitation

    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
     excited
    -1.69
    excited
    -1.62
     excite
    -1.43
     Excited
    -1.41
     exciting
    -1.40
     excitement
    -1.28
     excites
    -1.27
    Exciting
    -1.25
    Excited
    -1.25
     Exciting
    -1.23
    POSITIVE LOGITS
    ly
    0.77
     by
    0.56
     against
    0.50
     latter
    0.50
     and
    0.46
    ので
    0.46
     back
    0.45
     نظر
    0.45
     accordingly
    0.44
     سبيل
    0.44
    Activations Density 0.303%

    No Known Activations