© 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. 0-CLT-HP
    7. 45589
    Prev
    Next
    INDEX
    Explanations

    budgets and humans

    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
     createState
    -0.57
    AddAttribute
    -0.56
    EndInit
    -0.53
     SIMBAD
    -0.50
    @[+][
    -0.49
     OnInit
    -0.48
     ویکی‌پدیا
    -0.48
    OrNil
    -0.48
    󠁢
    -0.48
     Preferencias
    -0.47
    POSITIVE LOGITS
     мәкал
    0.64
     Turks
    0.61
     Jezus
    0.60
     ancients
    0.57
     igenom
    0.57
     copertura
    0.57
     Byzantine
    0.56
     archaic
    0.56
     Algerian
    0.56
     olden
    0.55
    Activations Density 0.206%

    No Known Activations