© 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. 4-CLT-HP
    7. 2246
    Prev
    Next
    INDEX
    Explanations

    best

    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
    MigrationBuilder
    -0.71
     CreateTagHelper
    -0.71
     cherchés
    -0.70
     initComponents
    -0.67
     intéress
    -0.65
    出版年
    -0.64
    featureID
    -0.63
     marié
    -0.62
    BufferException
    -0.62
     newBuilder
    -0.62
    POSITIVE LOGITS
    нес
    0.60
    nachron
    0.49
    INCREF
    0.49
    []
    0.48
     Principal
    0.48
    ragan
    0.47
     Primary
    0.46
     reference
    0.46
    /**
    0.45
     contribution
    0.45
    Activations Density 0.007%

    No Known Activations