© 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. 96758
    Prev
    Next
    INDEX
    Explanations

    most

    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
     currently
    -1.07
    currently
    -0.95
     Currently
    -0.91
     actuellement
    -0.91
    Currently
    -0.91
     derzeit
    -0.80
     presently
    -0.80
     atualmente
    -0.74
     actualmente
    -0.74
     now
    -0.73
    POSITIVE LOGITS
     autorytatywna
    0.84
     للمعارف
    0.81
     Meksiku
    0.80
     مشين
    0.79
     الحره
    0.78
     الرياضيه
    0.75
    __":
    0.73
    kháu
    0.72
    __':
    0.69
     afterward
    0.69
    Activations Density 0.156%

    No Known Activations