© 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. 4-CLT-HP
    7. 3293
    Prev
    Next
    INDEX
    Explanations

    surveys and interviews

    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
     semula
    -0.59
    .
    -0.57
     respectivas
    -0.55
     mesmas
    -0.55
     åt
    -0.55
     mesmos
    -0.54
     ajuns
    -0.53
     femininas
    -0.52
     to
    -0.52
     díl
    -0.52
    POSITIVE LOGITS
    NameInMap
    0.79
     people
    0.73
    ]--;
    0.66
     vendors
    0.63
     clients
    0.63
     a
    0.62
     clinicians
    0.62
     producers
    0.61
     experts
    0.61
     StatefulWidget
    0.61
    Activations Density 0.005%

    No Known Activations