© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4737
    Prev
    Next
    INDEX
    Explanations

    non-alphabetical characters

    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
     CreateTagHelper
    -0.62
     nahilalakip
    -0.62
    GeoNames
    -0.60
    Tikang
    -0.58
     ThemeData
    -0.57
    AutoScaleMode
    -0.57
    expandindo
    -0.56
     <>",
    -0.56
    Билгалдахарш
    -0.56
     hairpin
    -0.56
    POSITIVE LOGITS
    ley
    0.77
    LEY
    0.58
     المعيارى
    0.51
    ysy
    0.50
    ely
    0.49
    orsky
    0.48
    garve
    0.47
    ophyllum
    0.47
    eley
    0.47
    aly
    0.46
    Activations Density 0.003%

    No Known Activations