© 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. 930
    Prev
    Next
    INDEX
    Explanations

    academic/scientific text

    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
     للاسماء
    -0.99
     Мексичка
    -0.82
    rungsseite
    -0.80
    featureID
    -0.77
    GIVEREF
    -0.75
    الإنجليزية
    -0.75
     يتيمه
    -0.73
     ModelExpression
    -0.73
    AutoScaleMode
    -0.72
    FormTagHelper
    -0.72
    POSITIVE LOGITS
    اضر
    0.49
     Previously
    0.48
     vast
    0.47
     bizarre
    0.47
     unfamiliar
    0.47
     strange
    0.46
     kimse
    0.44
     quæ
    0.44
     Deadly
    0.43
     normally
    0.43
    Activations Density 0.001%

    No Known Activations