© 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. 73696
    Prev
    Next
    INDEX
    Explanations

    Know

    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
    новниш
    -0.70
    tanleria
    -0.68
     betweenstory
    -0.66
     ivelany
    -0.65
     الرياضيه
    -0.65
    elemField
    -0.64
    CppMethod
    -0.63
     kaarangay
    -0.62
    Autoritní
    -0.61
    IntoConstraints
    -0.59
    POSITIVE LOGITS
    -
    0.71
     Know
    0.63
    Know
    0.60
     know
    0.59
    re
    0.56
    know
    0.56
    Ren
    0.55
     Ren
    0.55
     Acknowled
    0.55
    知
    0.54
    Activations Density 0.001%

    No Known Activations