© 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. 1564
    Prev
    Next
    INDEX
    Explanations

    official documents/programs

    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
     panel
    -0.72
     Commercial
    -0.66
     commercial
    -0.64
     proportion
    -0.63
     panels
    -0.63
    Commercial
    -0.62
    commercial
    -0.61
     Panels
    -0.61
    PANEL
    -0.60
    panels
    -0.60
    POSITIVE LOGITS
    ist
    1.17
    ists
    1.02
    ization
    0.90
    ism
    0.85
    ized
    0.82
    ation
    0.80
    ary
    0.80
    ise
    0.79
    izing
    0.79
    ality
    0.78
    Activations Density 0.117%

    No Known Activations