© 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. 12289
    Prev
    Next
    INDEX
    Explanations

    research/technical documents

    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
     AssemblyCompany
    -0.73
     transfieras
    -0.69
     Roskov
    -0.68
    
    -0.64
     vanta
    -0.61
     converges
    -0.60
    αρα
    -0.59
    ंदीखरीदारी
    -0.57
    mbolos
    -0.56
    Weiterlesen
    -0.56
    POSITIVE LOGITS
    riwal
    0.55
    apnews
    0.54
    存于互联网档案馆
    0.53
    \
    0.52
    phosa
    0.50
    avax
    0.50
    wand
    0.48
     otomatig
    0.48
    lactin
    0.48
    Sur
    0.48
    Activations Density 0.003%

    No Known Activations