© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12076
    Prev
    Next
    INDEX
    Explanations

    drug

    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
     n
    -0.61
     d
    -0.59
     te
    -0.58
     des
    -0.55
     de
    -0.54
     B
    -0.51
     une
    -0.50
     "
    -0.50
     H
    -0.50
     na
    -0.50
    POSITIVE LOGITS
     يتيمه
    0.98
     AssemblyCompany
    0.75
     дописавши
    0.73
     Drapeau
    0.72
    AntiForgeryToken
    0.71
    
    0.71
     سكانية
    0.68
     ostavi
    0.67
     varandra
    0.67
    )}]{
    0.65
    Activations Density 0.212%

    No Known Activations