© 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. 20-CLT-HP
    7. 75645
    Prev
    Next
    INDEX
    Explanations

    being clear

    np_max-act-logits · 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
    mybatisplus
    -0.71
     estimés
    -0.65
    <bos>
    -0.63
    χρι
    -0.57
    ciclopedia
    -0.52
    Ծանոթ
    -0.50
     correctes
    -0.49
     Quelles
    -0.49
     يتيمه
    -0.49
    Collegamenti
    -0.48
    POSITIVE LOGITS
     clear
    1.06
     apparent
    0.88
     abundantly
    0.76
    clear
    0.74
    mergeFrom
    0.70
    apparent
    0.69
     plain
    0.69
     obvious
    0.62
     aparente
    0.61
     g
    0.60
    Activations Density 0.003%

    No Known Activations