© 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. 45354
    Prev
    Next
    INDEX
    Explanations

    Cedar

    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
     myſelf
    -1.83
     Jefus
    -1.80
     Houſe
    -1.71
     itſelf
    -1.70
     Efq
    -1.68
     purpoſe
    -1.63
     houſe
    -1.63
     Reſ
    -1.62
     themſelves
    -1.61
     Diſ
    -1.61
    POSITIVE LOGITS
    a
    0.98
    o
    0.90
    ians
    0.73
    i
    0.72
    e
    0.70
    es
    0.62
    ی
    0.59
    -------------</
    0.57
    AddHtmlAttribute
    0.57
    ian
    0.56
    Activations Density 0.066%

    No Known Activations