© 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. 92563
    Prev
    Next
    INDEX
    Explanations

    connection/link

    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
     link
    -1.90
     connection
    -1.87
     Link
    -1.41
     Connection
    -1.39
    connection
    -1.38
     connect
    -1.37
    Connection
    -1.26
     CONNECTION
    -1.18
    Link
    -1.11
     connexion
    -1.09
    POSITIVE LOGITS
     pouvoit
    0.71
     frontale
    0.68
     étoit
    0.67
     anteriore
    0.67
     newBuilder
    0.67
    i
    0.67
     fotografico
    0.65
     feroit
    0.65
    points
    0.64
    spots
    0.64
    Activations Density 0.048%

    No Known Activations