© 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. 72815
    Prev
    Next
    INDEX
    Explanations

    Code and technical descriptions

    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
    XmlAccessorType
    -0.57
    multer
    -0.55
    verwijspagina
    -0.55
    зулта
    -0.52
    plas
    -0.47
     povezave
    -0.47
    DataContract
    -0.46
    ]<<"
    -0.46
    thée
    -0.46
    lň
    -0.45
    POSITIVE LOGITS
     Kyu
    0.62
    tagHelperRunner
    0.57
    InjectAttribute
    0.56
     indisponible
    0.55
    RegressionTest
    0.53
    ={({
    0.53
    COUVER
    0.52
    MessageOf
    0.52
    kyu
    0.50
     Monfieur
    0.50
    Activations Density 0.000%

    No Known Activations