© 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. 93137
    Prev
    Next
    INDEX
    Explanations

    you

    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
     disambiguazione
    -0.93
     gynhyrchwyd
    -0.85
    évaluateur
    -0.82
    tangentMode
    -0.80
    RegressionTest
    -0.76
    ثيق
    -0.75
     ivelany
    -0.75
     MainAxisSize
    -0.74
    AndEndTag
    -0.74
    مصادر
    -0.74
    POSITIVE LOGITS
     siihen
    0.42
     täh
    0.41
    同
    0.39
     thereon
    0.38
    I
    0.38
     yardımcı
    0.37
     derecho
    0.37
    仕
    0.37
    dig
    0.37
    Yeah
    0.36
    Activations Density 0.012%

    No Known Activations