© 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. 40998
    Prev
    Next
    INDEX
    Explanations

    complete

    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
     protocol
    -0.89
     Protocol
    -0.89
    Protocol
    -0.77
     PROTOCOL
    -0.70
    protocol
    -0.67
     completion
    -0.62
     completeness
    -0.62
     protocolo
    -0.62
    oa̍t
    -0.60
     Protocols
    -0.58
    POSITIVE LOGITS
    Viited
    0.56
    AndEndTag
    0.55
    [...,
    0.54
    ênis
    0.52
    outine
    0.52
    ierre
    0.52
    ftar
    0.52
     affer
    0.52
     Leche
    0.51
    Espèce
    0.51
    Activations Density 0.122%

    No Known Activations