© 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. 4-CLT-HP
    7. 2211
    Prev
    Next
    INDEX
    Explanations

    with

    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
    Jîn
    -0.54
     voltmeter
    -0.51
    homonymie
    -0.50
     Helped
    -0.49
     Мексичка
    -0.49
    şekkür
    -0.48
     indisponible
    -0.48
    findpost
    -0.48
    serva
    -0.47
    inigungs
    -0.47
    POSITIVE LOGITS
     intention
    0.62
     objective
    0.62
     intent
    0.61
     proposals
    0.59
     aim
    0.58
     상세
    0.58
     quæ
    0.56
     intentions
    0.56
     plans
    0.55
    CompleteListener
    0.55
    Activations Density 0.003%

    No Known Activations