© 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. 1-CLT-HP
    7. 45999
    Prev
    Next
    INDEX
    Explanations

    language

    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
     language
    -1.25
    language
    -1.13
    Language
    -1.12
     Language
    -1.06
     languages
    -0.90
     LANGUAGE
    -0.86
    LANGUAGE
    -0.84
    languages
    -0.82
    Languages
    -0.80
    语言
    -0.78
    POSITIVE LOGITS
     الحره
    0.81
    Xna
    0.78
    tagHelperRunner
    0.77
     AssemblyTitle
    0.75
    \{\\
    0.73
     propOrder
    0.73
    ]")]
    0.72
     kasarigan
    0.72
    fjspx
    0.71
    DoubleQuotes
    0.68
    Activations Density 0.035%

    No Known Activations