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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41283
    Prev
    Next
    INDEX
    Explanations

    people

    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
    openzeppelin
    -0.55
     jamur
    -0.46
    gatsby
    -0.45
     désolés
    -0.45
    yticks
    -0.45
    dropIfExists
    -0.44
     up
    -0.44
     sendiri
    -0.43
    HIRE
    -0.42
    m
    -0.41
    POSITIVE LOGITS
     myſelf
    0.86
     nakalista
    0.78
     theſe
    0.78
     houſe
    0.76
     kaarangay
    0.75
     themſelves
    0.72
     Monfieur
    0.72
     leaſt
    0.72
     purpoſe
    0.72
    )':
    0.71
    Activations Density 1.403%

    No Known Activations