© 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. 5003
    Prev
    Next
    INDEX
    Explanations

    contrast

    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
     though
    -0.54
     AspNetCore
    -0.43
     himo
    -0.43
    ще
    -0.39
     however
    -0.39
     THOUGH
    -0.38
    though
    -0.36
     Biôgrafia
    -0.35
    SharedCtor
    -0.35
    Geplaatst
    -0.35
    POSITIVE LOGITS
     Wicidata
    0.77
     Theſe
    0.72
     gioielli
    0.69
    actéristique
    0.69
    これも
    0.69
     conçus
    0.68
    .³
    0.68
    featureID
    0.68
     rencontré
    0.67
    Становништво
    0.66
    Activations Density 0.008%

    No Known Activations