© 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. 90861
    Prev
    Next
    INDEX
    Explanations

    ily

    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
     loss
    -1.27
    loss
    -0.83
     Loss
    -0.82
    Loss
    -0.77
     LOSS
    -0.69
     assessment
    -0.64
    ily
    -0.63
     pérdida
    -0.57
     “
    -0.56
     mass
    -0.54
    POSITIVE LOGITS
     متعلقه
    1.20
     виправивши
    1.11
    SourceChecksum
    1.06
    complexContent
    0.99
    MigrationBuilder
    0.99
    httphttps
    0.98
    DeleteBehavior
    0.97
    تقاوى
    0.96
     ExecuteAsync
    0.94
     CreateTagHelper
    0.94
    Activations Density 0.714%

    No Known Activations