© 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. 5-CLT-HP
    7. 2921
    Prev
    Next
    INDEX
    Explanations

    sustainable

    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
    InSection
    -0.61
     CreateTagHelper
    -0.59
     manfaat
    -0.54
    kunft
    -0.51
     InputDecoration
    -0.51
    }))
    -0.49
     voudrais
    -0.49
    UnitTesting
    -0.49
    queryInterface
    -0.47
    клопе
    -0.47
    POSITIVE LOGITS
     modes
    0.60
     forms
    0.58
     Modes
    0.56
     Forms
    0.54
     patterns
    0.52
     form
    0.52
    Modes
    0.52
     Form
    0.52
     FORMS
    0.51
     ويكيپيديا
    0.51
    Activations Density 0.001%

    No Known Activations