© 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. 4-CLT-HP
    7. 2723
    Prev
    Next
    INDEX
    Explanations

    screen resolution/image size

    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
     dialects
    -0.41
     viewType
    -0.40
     fibrillation
    -0.40
    alej
    -0.39
    VIAF
    -0.39
    瞰
    -0.39
    //
    -0.38
    EndProject
    -0.38
    autorest
    -0.38
     نقص
    -0.38
    POSITIVE LOGITS
     typelib
    0.72
     "..\..\..\
    0.69
     /\.
    0.67
     suivez
    0.66
     tartalomajánló
    0.64
     للمعارف
    0.64
     /\.(
    0.63
     étoient
    0.63
     femininas
    0.63
     journaux
    0.62
    Activations Density 0.082%

    No Known Activations