© 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. 5-CLT-HP
    7. 5617
    Prev
    Next
    INDEX
    Explanations

    fantasy/gaming-related

    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
     neuve
    -0.55
     möjligt
    -0.53
    ckså
    -0.52
     sauvages
    -0.52
     čierna
    -0.50
     conseguenza
    -0.49
     Unido
    -0.48
     cadeaux
    -0.47
     cérami
    -0.47
    IonicModule
    -0.47
    POSITIVE LOGITS
    AccessorTable
    0.73
    GraphicsUnit
    0.70
    IsContent
    0.64
    ened
    0.59
    lessed
    0.58
    istically
    0.58
    binder
    0.56
    WriteTagHelper
    0.56
     Diakses
    0.56
    脚注の使い方
    0.54
    Activations Density 0.001%

    No Known Activations