© 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. 97180
    Prev
    Next
    INDEX
    Explanations

    ma or physiological

    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
     appropriate
    -0.86
    appropriate
    -0.85
     relevant
    -0.75
     @"/
    -0.70
     suitable
    -0.69
    NullCheck
    -0.68
    relevant
    -0.67
     Appropriate
    -0.67
    suitable
    -0.66
     geeigne
    -0.65
    POSITIVE LOGITS
    dataProvider
    0.47
     paraph
    0.47
     StatefulWidget
    0.46
     fared
    0.46
     nails
    0.44
     wore
    0.44
     morals
    0.44
    Tira
    0.43
     Nicholls
    0.43
     senses
    0.42
    Activations Density 1.107%

    No Known Activations