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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3166
    Prev
    Next
    INDEX
    Explanations

    /

    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
    -
    -0.53
     indi
    -0.46
     gro
    -0.46
     pier
    -0.44
     see
    -0.44
     saw
    -0.44
    ier
    -0.44
     is
    -0.44
    ставить
    -0.43
     
    -0.43
    POSITIVE LOGITS
     étoient
    0.75
     pitié
    0.73
     pouvoit
    0.72
     auroit
    0.71
     étoit
    0.71
    تقاوى
    0.71
     debout
    0.71
     Monfieur
    0.70
     découver
    0.70
     avoient
    0.70
    Activations Density 0.001%

    No Known Activations