Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91767
    Prev
    Next
    INDEX
    Explanations

    communication

    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
     communication
    -1.30
    communication
    -1.20
     communications
    -1.08
     Communication
    -1.03
    Communication
    -0.97
     COMMUNICATION
    -0.95
    communications
    -0.93
     Communications
    -0.86
    COMMUNIC
    -0.86
     comunicación
    -0.82
    POSITIVE LOGITS
     estimés
    0.60
    >());
    0.56
     gap
    0.54
     passée
    0.52
     <>",
    0.52
    })));
    0.51
     recev
    0.51
     Proving
    0.51
     horaire
    0.50
    ">//
    0.50
    Activations Density 0.024%

    No Known Activations