© 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. 739
    Prev
    Next
    INDEX
    Explanations

    Questions and explanations

    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
     знаем
    -0.51
    oa̍t
    -0.48
     sanno
    -0.47
     saben
    -0.45
    sequence
    -0.43
    Sequence
    -0.41
     sabemos
    -0.41
    følgelig
    -0.41
     sabes
    -0.39
     correspon
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.93
     >=",
    0.81
    __":
    0.81
    CppMethod
    0.78
    IMPORTED
    0.76
     متعلقه
    0.74
    ]]:
    0.73
     autorytatywna
    0.72
    yship
    0.70
    最快更新
    0.70
    Activations Density 0.028%

    No Known Activations