© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91347
    Prev
    Next
    INDEX
    Explanations

    COVID

    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
     مشين
    -0.88
     nakalista
    -0.87
     CreateTagHelper
    -0.85
    ]")]
    -0.82
    ReusableCell
    -0.79
     PhpStorm
    -0.78
    Hochspringen
    -0.76
    CloseOperation
    -0.76
    posedge
    -0.75
    RUnlock
    -0.75
    POSITIVE LOGITS
    -
    0.93
    1
    0.62
    2
    0.45
    7
    0.42
    ူ
    0.41
    P
    0.41
    <table>
    0.40
    +
    0.39
    8
    0.38
    9
    0.38
    Activations Density 0.000%

    No Known Activations