© 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. 5-CLT-HP
    7. 92971
    Prev
    Next
    INDEX
    Explanations

    health issues

    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
    <bos>
    -0.95
    OGND
    -0.68
    httphttps
    -0.63
    Happ
    -0.60
    הערות
    -0.60
    پاسخ
    -0.56
    fml
    -0.54
     bū
    -0.54
    óngase
    -0.54
    enumi
    -0.53
    POSITIVE LOGITS
     themselves
    0.57
    mentaux
    0.52
    hdashline
    0.49
    themselves
    0.47
     alike
    0.43
    WriteTagHelper
    0.43
    المناصب
    0.42
    csolódó
    0.42
     ========
    0.41
     ComVisible
    0.40
    Activations Density 0.002%

    No Known Activations