© 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. 20-CLT-HP
    7. 76442
    Prev
    Next
    INDEX
    Explanations

    kind

    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
     الدولى
    -0.82
    出版年
    -0.71
     fermés
    -0.68
    érêt
    -0.68
    AccessorTable
    -0.66
     avoient
    -0.65
     purpoſe
    -0.65
    esez
    -0.64
    Παραπομπές
    -0.63
    </caption>
    -0.62
    POSITIVE LOGITS
     sort
    1.69
     kind
    1.55
    sort
    1.34
     sorta
    1.30
     Sort
    1.27
    kind
    1.23
     kinda
    1.22
     Kind
    1.17
     sorts
    1.13
     SORT
    1.10
    Activations Density 0.008%

    No Known Activations