© 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. 3486
    Prev
    Next
    INDEX
    Explanations

    Focus

    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
    RegressionTest
    -0.48
     perciò
    -0.46
    ＝
    -0.44
    umba
    -0.42
     ayr
    -0.42
    立
    -0.41
     justru
    -0.41
     senare
    -0.40
    Hence
    -0.39
     riuscito
    -0.39
    POSITIVE LOGITS
    :✨
    0.89
     purpoſe
    0.82
     bezeichneter
    0.80
     oprot
    0.79
     NSCoder
    0.79
     pleaſure
    0.75
     greateſt
    0.75
     Roskov
    0.75
     Efq
    0.75
    IGraphics
    0.75
    Activations Density 0.000%

    No Known Activations