© 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. 0-CLT-HP
    7. 43554
    Prev
    Next
    INDEX
    Explanations

    technology, shale, legal documents

    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
    s
    -0.64
    es
    -0.59
    khi
    -0.54
    when
    -0.52
    itous
    -0.51
    SPE
    -0.50
     when
    -0.50
    WHEN
    -0.49
    ote
    -0.48
     oeste
    -0.47
    POSITIVE LOGITS
     وتسجيلات
    0.87
     autorytatywna
    0.81
     MainAxisSize
    0.81
    脚注の使い方
    0.79
    AndEndTag
    0.79
    TagMode
    0.74
     wireType
    0.71
    ="@+
    0.70
    %)$
    0.70
    enumi
    0.69
    Activations Density 0.844%

    No Known Activations