© 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. 0-CLT-HP
    7. 93803
    Prev
    Next
    INDEX
    Explanations

    ways

    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
     للاسماء
    -0.70
     myſelf
    -0.69
     houſe
    -0.66
     pleaſure
    -0.65
     avoient
    -0.64
     Efq
    -0.64
     vastaan
    -0.62
     pères
    -0.61
     tilbage
    -0.61
     referenties
    -0.60
    POSITIVE LOGITS
     to
    0.71
    tagHelper
    0.52
     like
    0.52
     t
    0.51
     of
    0.51
     so
    0.50
     Biophys
    0.50
     b
    0.49
    frac
    0.49
    DoubleQuotes
    0.49
    Activations Density 0.022%

    No Known Activations