© 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. 4-CLT-HP
    7. 4946
    Prev
    Next
    INDEX
    Explanations

    ard

    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
     DataLoader
    -0.52
     flèche
    -0.50
     demais
    -0.49
     Additive
    -0.49
    perror
    -0.45
     gouttes
    -0.45
    inary
    -0.44
     oublier
    -0.43
     poitrine
    -0.43
    cary
    -0.43
    POSITIVE LOGITS
     الحره
    0.74
     الاطلاع
    0.66
    تقاوى
    0.65
     ostavi
    0.64
     GenerationType
    0.63
    دانشنامهٔ
    0.62
     تضيفلها
    0.60
    EReference
    0.59
    verwijspagina
    0.58
     growing
    0.57
    Activations Density 0.000%

    No Known Activations