© 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. 43539
    Prev
    Next
    INDEX
    Explanations

    initialization

    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
    står
    -0.51
     betweenstory
    -0.51
    mergeFrom
    -0.49
    engan
    -0.47
    tede
    -0.47
     .”
    -0.47
     tia
    -0.46
    dion
    -0.46
    이의
    -0.45
     onze
    -0.44
    POSITIVE LOGITS
    ImageContext
    0.78
    AutoScaleMode
    0.76
    +#+#
    0.76
    WireFormatLite
    0.73
    arakhand
    0.71
     ExecuteAsync
    0.70
     AppCompatTheme
    0.69
    ymce
    0.69
    tanleria
    0.68
    تقاوى
    0.67
    Activations Density 1.562%

    No Known Activations