© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38382
    Prev
    Next
    INDEX
    Explanations

    Part

    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
    Part
    -1.00
     myſelf
    -0.86
     quæ
    -0.85
     themſelves
    -0.85
     itſelf
    -0.85
     Part
    -0.84
     ſtate
    -0.82
     geox
    -0.78
    ſelves
    -0.77
     uſed
    -0.77
    POSITIVE LOGITS
    !*\
    0.57
    ="@+
    0.54
     ->
    0.50
    (!__
    0.49
    visor
    0.48
    terie
    0.48
     des
    0.47
     للاسماء
    0.47
     div
    0.47
    decorate
    0.47
    Activations Density 0.047%

    No Known Activations