© 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. 94379
    Prev
    Next
    INDEX
    Explanations

    '

    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
    ContentAsync
    -1.05
     tartalomajánló
    -1.01
    تقاوى
    -0.95
    tagHelperRunner
    -0.88
    featureID
    -0.87
    saraba
    -0.85
     resourceCulture
    -0.84
    expandindo
    -0.82
     EconPapers
    -0.81
    Sucesor
    -0.80
    POSITIVE LOGITS
    usually
    0.52
    <bos>
    0.49
     usually
    0.48
     Usually
    0.46
     
    0.45
    ®
    0.44
    Usually
    0.44
     geralmente
    0.44
     biasanya
    0.43
    Климат
    0.42
    Activations Density 0.013%

    No Known Activations