© 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. 1833
    Prev
    Next
    INDEX
    Explanations

    protocol

    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
    -2.06
     Protocol
    -2.05
    Protocol
    -1.89
    protocol
    -1.85
     Protocols
    -1.59
     PROTOCOL
    -1.56
     protocols
    -1.55
     protocolo
    -1.54
     protocole
    -1.51
    PROTOCOL
    -1.38
    POSITIVE LOGITS
    IntoConstraints
    0.72
     Efq
    0.70
     referenties
    0.65
    bezpe
    0.64
    цездатний
    0.63
     poffe
    0.59
     Bote
    0.58
    EnableWeb
    0.58
    ComponentScan
    0.58
     Wikidata
    0.57
    Activations Density 0.082%

    No Known Activations