© 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. 45368
    Prev
    Next
    INDEX
    Explanations

    excellence

    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
     aerosols
    -0.71
     forums
    -0.65
    resident
    -0.65
    aeros
    -0.61
     excellence
    -0.61
     forum
    -0.60
     resident
    -0.60
    forum
    -0.58
     esternos
    -0.58
     aerosol
    -0.57
    POSITIVE LOGITS
     BorderRadius
    0.87
     Inquis
    0.65
    RectangleBorder
    0.64
     Schengen
    0.64
     AppColors
    0.61
     ujednoznacz
    0.60
     Toda
    0.58
    routeProvider
    0.58
     insuffisamment
    0.57
     MutableLiveData
    0.57
    Activations Density 0.153%

    No Known Activations