© 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. 5-CLT-HP
    7. 432
    Prev
    Next
    INDEX
    Explanations

    saying something

    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
     rätt
    -0.45
     perfeitamente
    -0.44
    to
    -0.43
    if
    -0.43
    post
    -0.43
    further
    -0.39
     vastaan
    -0.39
     correctamente
    -0.38
     unui
    -0.38
     hvis
    -0.37
    POSITIVE LOGITS
    tagHelperRunner
    0.94
     FetchType
    0.85
     AssemblyCulture
    0.84
     المعيارى
    0.84
    ftagPool
    0.83
    Rujuakan
    0.82
    ViewFeatures
    0.79
    AndEndTag
    0.79
    EndInit
    0.79
    WebControls
    0.79
    Activations Density 0.006%

    No Known Activations