© 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. 1-CLT-HP
    7. 11589
    Prev
    Next
    INDEX
    Explanations

    Quotations or code

    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
     “¿
    -0.56
    צלחה
    -0.53
     الحره
    -0.53
     amitié
    -0.52
     chrétiens
    -0.49
     Roskov
    -0.48
    FetchType
    -0.47
     purpoſe
    -0.47
     gauss
    -0.46
    UTERS
    -0.46
    POSITIVE LOGITS
     JTextArea
    0.58
     JpaRepository
    0.56
     Waray
    0.56
     Models
    0.55
    Aiheesta
    0.54
     Hall
    0.54
     المعيارى
    0.54
    thalle
    0.54
    TypedDataSet
    0.54
     Co
    0.53
    Activations Density 0.006%

    No Known Activations