© 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. 90763
    Prev
    Next
    INDEX
    Explanations

    standards and laws

    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
     standards
    -1.22
    standards
    -0.99
     STANDARDS
    -0.99
     Standards
    -0.92
    Standards
    -0.91
     rules
    -0.70
     laws
    -0.69
    标准
    -0.67
     estándares
    -0.66
     стандар
    -0.65
    POSITIVE LOGITS
    بوابة
    0.69
    djangoproject
    0.66
     décid
    0.65
    揄
    0.63
    ništvo
    0.62
     CanadaChoose
    0.62
     végét
    0.62
    __*/
    0.62
     synag
    0.61
     LCCN
    0.61
    Activations Density 0.079%

    No Known Activations