© 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. 76969
    Prev
    Next
    INDEX
    Explanations

    Names or foreign languages

    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
     chré
    -0.60
     pauvres
    -0.56
    ])[
    -0.54
    ırlar
    -0.54
     religieuses
    -0.54
    )}</
    -0.53
     ferons
    -0.53
     trouverez
    -0.52
     automatiques
    -0.52
     cesse
    -0.51
    POSITIVE LOGITS
     متعلقه
    0.66
     Numerade
    0.55
    thenes
    0.51
    показания
    0.51
     Mes
    0.50
     Books
    0.50
    tagHelperRunner
    0.50
    ulele
    0.49
     Aires
    0.49
    íritu
    0.49
    Activations Density 0.007%

    No Known Activations