© 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. 1977
    Prev
    Next
    INDEX
    Explanations

    repaired

    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
     repaired
    -1.12
     ring
    -0.57
     ringer
    -0.50
     Leopoldo
    -0.50
     proximity
    -0.50
     mended
    -0.49
    ring
    -0.49
     repairs
    -0.48
    ollectionView
    -0.47
     handi
    -0.47
    POSITIVE LOGITS
     يتيمه
    0.62
    ArgsConstructor
    0.59
    webElementXpaths
    0.58
     OnInit
    0.57
     femininos
    0.56
     EconPapers
    0.56
     vaisseaux
    0.56
    ValueStyle
    0.55
    ínű
    0.55
     CreateTagHelper
    0.54
    Activations Density 0.051%

    No Known Activations