© 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. 20-CLT-HP
    7. 77093
    Prev
    Next
    INDEX
    Explanations

    commercial activity

    np_max-act-logits · 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
     AssemblyCulture
    -0.69
     nôtre
    -0.68
     planète
    -0.67
    boks
    -0.65
     obé
    -0.62
     répon
    -0.61
     réve
    -0.60
     hiér
    -0.60
     ruota
    -0.59
    Fprintf
    -0.59
    POSITIVE LOGITS
     capacity
    0.49
     power
    0.49
    Obrázky
    0.47
    
    0.41
     dises
    0.38
    PRNewswire
    0.36
    bootstrapcdn
    0.35
    '</
    0.35
    mgp
    0.35
     Capacity
    0.35
    Activations Density 0.000%

    No Known Activations