© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91953
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    AsUp
    -0.77
    parsedMessage
    -0.75
    MessageOf
    -0.75
     '\\;'
    -0.71
    PropertyChanging
    -0.71
    writeField
    -0.70
    esModule
    -0.68
    IsContent
    -0.68
    AddTagHelper
    -0.67
    jsonwebtoken
    -0.67
    POSITIVE LOGITS
     fun
    0.50
     smart
    0.47
     fair
    0.47
     patient
    0.44
    smart
    0.43
     simple
    0.42
    quitous
    0.41
     safe
    0.41
     global
    0.41
    safe
    0.40
    Activations Density 0.003%

    No Known Activations