© 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. 90798
    Prev
    Next
    INDEX
    Explanations

    attempts and observations

    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
     itſelf
    -0.94
     Wikimedijinoj
    -0.93
    lably
    -0.93
    󠁴
    -0.91
    tubers
    -0.90
     isInitialized
    -0.89
     Савезне
    -0.87
     pleaſure
    -0.87
    othed
    -0.86
     ब्रेकडाउन
    -0.86
    POSITIVE LOGITS
    multer
    0.59
     
    0.58
     “
    0.55
     <
    0.50
     for
    0.50
    .
    0.49
    ’
    0.48
    a
    0.48
    <eos>
    0.47
     (
    0.46
    Activations Density 0.082%

    No Known Activations