© 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. 44050
    Prev
    Next
    INDEX
    Explanations

    America

    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
     American
    -2.44
     America
    -2.16
    American
    -2.08
     american
    -1.77
    America
    -1.71
     AMERICAN
    -1.70
     Americans
    -1.57
    american
    -1.57
     america
    -1.55
     AMERICA
    -1.51
    POSITIVE LOGITS
     itſelf
    1.23
     HasFactory
    1.21
     ―――――
    1.20
    +#+#
    1.19
     Normdatei
    1.18
     الحره
    1.16
     photolibrary
    1.16
     صوتيه
    1.14
     виправивши
    1.13
    SequentialGroup
    1.12
    Activations Density 0.228%

    No Known Activations