© 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. 0-CLT-HP
    7. 42502
    Prev
    Next
    INDEX
    Explanations

    Inpatient medical care

    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
     disambiguazione
    -0.87
    awaiter
    -0.81
    ViewFeatures
    -0.76
     Silurian
    -0.75
    ValueStyle
    -0.74
    ANDUM
    -0.72
    Personendaten
    -0.72
     utafitiHapana
    -0.71
     aloud
    -0.70
    annica
    -0.70
    POSITIVE LOGITS
    ed
    0.54
    راسیون
    0.49
    o
    0.46
     κατά
    0.42
    edades
    0.41
    ]].
    0.41
    adi
    0.38
     ря
    0.38
    …).
    0.38
    e
    0.38
    Activations Density 0.133%

    No Known Activations