© 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. 98273
    Prev
    Next
    INDEX
    Explanations

    to

    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
     today
    -0.77
     aujourd
    -0.67
    Today
    -0.63
     heute
    -0.63
     hoy
    -0.60
     now
    -0.60
     hoje
    -0.60
     oggi
    -0.59
    today
    -0.59
     Today
    -0.59
    POSITIVE LOGITS
    Билгалдахарш
    0.79
     itſelf
    0.75
     foon
    0.75
     fubject
    0.72
     poffible
    0.69
     Anſ
    0.67
     perſon
    0.64
     Reſ
    0.64
     themſelves
    0.62
     ſeveral
    0.62
    Activations Density 0.025%

    No Known Activations