© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 46066
    Prev
    Next
    INDEX
    Explanations

    traditional/conventional

    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
     HasFactory
    -0.66
     CreateTagHelper
    -0.63
     Exacts
    -0.58
     garanzia
    -0.57
    AddTagHelper
    -0.54
     financiera
    -0.53
     iprot
    -0.52
     kabát
    -0.52
     démocr
    -0.52
    hubanes
    -0.51
    POSITIVE LOGITS
     dri
    0.53
    elis
    0.52
     disambiguazione
    0.51
    hnung
    0.50
    Viited
    0.49
     AssemblyCompany
    0.49
    permitAll
    0.47
     car
    0.47
     चीज़ों
    0.47
     drive
    0.46
    Activations Density 0.107%

    No Known Activations