© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73534
    Prev
    Next
    INDEX
    Explanations

    Session

    np_max-act-logits · 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
     définiti
    -0.76
     religieuses
    -0.75
     חיצוניים
    -0.75
     étrangères
    -0.74
     régl
    -0.73
     élevées
    -0.72
     connus
    -0.71
     préparé
    -0.70
     découver
    -0.70
     nationaux
    -0.70
    POSITIVE LOGITS
     principal
    0.63
     concept
    0.63
     system
    0.61
    AxisAlignment
    0.57
     process
    0.54
    tagHelper
    0.46
     Erb
    0.46
     princi
    0.46
     vain
    0.45
     syst
    0.44
    Activations Density 0.000%

    No Known Activations