© 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. 2347
    Prev
    Next
    INDEX
    Explanations

    So

    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
     صوتيه
    -0.70
     ModelExpression
    -0.67
    Diwedd
    -0.65
    AsUp
    -0.60
     Administrativna
    -0.60
     propOrder
    -0.60
     وتسجيلات
    -0.58
     vermelhas
    -0.58
     remplacé
    -0.58
    RunAsync
    -0.58
    POSITIVE LOGITS
    ,
    0.52
    さっき
    0.49
     Previously
    0.49
    όμε
    0.48
    irah
    0.46
     Earlier
    0.46
    GOTREF
    0.45
    +:+
    0.45
     previously
    0.45
     Heard
    0.44
    Activations Density 0.015%

    No Known Activations