© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43020
    Prev
    Next
    INDEX
    Explanations

    language/translation

    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
    -2.03
     Language
    -1.80
    language
    -1.78
    Language
    -1.63
     LANGUAGE
    -1.55
    LANGUAGE
    -1.28
     lenguaje
    -1.27
    语言
    -1.26
     langage
    -1.15
     Sprache
    -1.11
    POSITIVE LOGITS
     الحره
    0.88
     الرياضيه
    0.83
    +#+#
    0.81
    DeleteBehavior
    0.81
     سكانية
    0.78
     betweenstory
    0.77
     везе
    0.76
    TypedDataSet
    0.74
    évaluateur
    0.74
    oa̍t
    0.73
    Activations Density 0.036%

    No Known Activations