© 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. 352
    Prev
    Next
    INDEX
    Explanations

    youth

    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
    تقاوى
    -0.83
    thâu
    -0.82
    DockStyle
    -0.80
    \{\\
    -0.75
    Билгалдахарш
    -0.72
    цездатний
    -0.72
     AssemblyProduct
    -0.70
    !*\
    -0.70
    orsese
    -0.69
    richTextPanel
    -0.68
    POSITIVE LOGITS
    -
    0.48
    ual
    0.43
     anaknya
    0.41
     anak
    0.41
     cartera
    0.39
    Otras
    0.39
     dessen
    0.38
    ؤلاء
    0.37
    ens
    0.37
    ish
    0.37
    Activations Density 0.003%

    No Known Activations