© 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. 5-CLT-HP
    7. 94580
    Prev
    Next
    INDEX
    Explanations

    the

    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
    AutoScaleMode
    -0.72
    FormTagHelper
    -0.72
    basicConfig
    -0.70
    errHandler
    -0.68
     समीक्षाओं
    -0.68
     CreateTagHelper
    -0.67
    Atoi
    -0.61
    parsedMessage
    -0.61
     kaarangay
    -0.60
    GEBURTSDATUM
    -0.60
    POSITIVE LOGITS
     a
    0.57
     his
    0.57
     our
    0.56
     an
    0.56
     something
    0.55
    طني
    0.49
     another
    0.49
     your
    0.48
     still
    0.48
     really
    0.48
    Activations Density 0.018%

    No Known Activations