© 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. 1-CLT-HP
    7. 14774
    Prev
    Next
    INDEX
    Explanations

    thyroid

    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
     thyroid
    -1.41
     Thyroid
    -1.30
    thyroidism
    -1.23
    thyroid
    -1.15
     démocr
    -0.69
    tahankan
    -0.64
    ниципа
    -0.63
    enfance
    -0.60
     tremp
    -0.59
     originaux
    -0.59
    POSITIVE LOGITS
    al
    0.81
    s
    0.69
    ️
    0.59
    ی
    0.55
     /\.
    0.55
    itis
    0.53
    /*---
    0.52
    Према
    0.52
    ally
    0.50
    ic
    0.49
    Activations Density 0.005%

    No Known Activations