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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 977
    Prev
    Next
    INDEX
    Explanations

    secure

    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
    GEBURTSDATUM
    -1.09
    secure
    -1.02
    تقاوى
    -0.98
    Personensuche
    -0.96
     secure
    -0.94
     CreateTagHelper
    -0.93
     resourceCulture
    -0.91
     AssemblyCulture
    -0.87
     sécur
    -0.87
    httphttps
    -0.87
    POSITIVE LOGITS
     model
    0.58
     key
    0.56
     association
    0.55
     p
    0.54
    -
    0.50
     "
    0.49
     level
    0.49
     reference
    0.49
    ,
    0.49
     I
    0.48
    Activations Density 0.817%

    No Known Activations