© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45284
    Prev
    Next
    INDEX
    Explanations

    connect

    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
     connect
    -1.11
     connects
    -0.98
     conecta
    -0.94
     connecting
    -0.92
    connect
    -0.85
     connected
    -0.81
     Connect
    -0.77
    connected
    -0.76
     conectados
    -0.75
    Connecting
    -0.71
    POSITIVE LOGITS
     itſelf
    0.90
     ་་
    0.81
     myſelf
    0.77
     ―――――
    0.77
     pleaſure
    0.75
     themſelves
    0.75
    )");
    0.75
    ")));
    0.73
     himſelf
    0.72
     Forumite
    0.72
    Activations Density 0.427%

    No Known Activations