© 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. 0-CLT-HP
    7. 97035
    Prev
    Next
    INDEX
    Explanations

    architecture

    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
     Architecture
    -1.18
     architecture
    -1.09
     architectural
    -1.03
     Architect
    -1.01
    architecture
    -1.01
    Architecture
    -0.98
    SourceChecksum
    -0.97
     architects
    -0.97
    architectural
    -0.96
     Architects
    -0.94
    POSITIVE LOGITS
    o
    0.68
    ed
    0.67
    i
    0.66
    a
    0.63
    e
    0.62
    es
    0.57
    tant
    0.57
    t
    0.56
    ing
    0.51
    g
    0.48
    Activations Density 0.126%

    No Known Activations