© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4356
    Prev
    Next
    INDEX
    Explanations

    only

    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
     חיצוניים
    -0.74
    Personensuche
    -0.72
     estekak
    -0.69
     المعيارى
    -0.68
    adaptiveStyles
    -0.67
    MessageTagHelper
    -0.65
    DeleteBehavior
    -0.65
    MLLoader
    -0.65
    tagHelperRunner
    -0.64
    parsedMessage
    -0.63
    POSITIVE LOGITS
     a
    0.67
     an
    0.58
    WithIOException
    0.57
     stammer
    0.51
    ('/:
    0.51
     graça
    0.50
     ressemb
    0.48
    Хро
    0.48
     pubblici
    0.48
     alış
    0.46
    Activations Density 0.003%

    No Known Activations