© 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. 96814
    Prev
    Next
    INDEX
    Explanations

    requests for help

    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
    archiviato
    -0.54
     consultato
    -0.52
    flies
    -0.50
    setupUi
    -0.50
    ьаж
    -0.50
     незавершена
    -0.49
    بوابة
    -0.49
     ExecuteAsync
    -0.48
     deserving
    -0.48
     clearing
    -0.46
    POSITIVE LOGITS
     judiciales
    0.65
     policiales
    0.60
     extérieures
    0.60
    yttö
    0.59
     hovor
    0.58
     pretože
    0.57
     savons
    0.57
     déclarations
    0.56
    >*/
    0.56
    følgelig
    0.56
    Activations Density 0.016%

    No Known Activations