© 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. 39001
    Prev
    Next
    INDEX
    Explanations

    treasury

    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
     treasury
    -0.90
     Secretary
    -0.88
     secretary
    -0.83
    Secretary
    -0.82
     quæ
    -0.81
    ſelves
    -0.77
    secretary
    -0.75
     SECRETARY
    -0.74
     Diſ
    -0.74
    <()>
    -0.74
    POSITIVE LOGITS
     of
    0.78
    invokeLater
    0.60
    aarrggbb
    0.50
     ddelweddau
    0.49
     ensures
    0.47
    /**
    0.47
    Ensure
    0.47
     fluid
    0.45
     Ensure
    0.45
    fluid
    0.45
    Activations Density 1.599%

    No Known Activations