© 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. 2408
    Prev
    Next
    INDEX
    Explanations

    Written documents

    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
     INTERESAR
    -0.47
    Profiler
    -0.47
     over
    -0.41
     lack
    -0.40
    ].
    -0.40
    涵
    -0.40
    ng
    -0.40
    !
    -0.39
     Fehl
    -0.38
     SULL
    -0.38
    POSITIVE LOGITS
     дописавши
    0.92
    DockStyle
    0.87
    expandindo
    0.86
    +#+#
    0.86
    SourceChecksum
    0.84
    Geplaatst
    0.81
     AssemblyCulture
    0.81
    complexContent
    0.80
     للمعارف
    0.80
     فريبيس
    0.78
    Activations Density 0.003%

    No Known Activations