© 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. 0-CLT-HP
    7. 42255
    Prev
    Next
    INDEX
    Explanations

    η

    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
     list
    -0.92
     listing
    -0.74
     List
    -0.61
     gezet
    -0.56
     lista
    -0.54
     Told
    -0.54
     ModelExpression
    -0.54
    itti
    -0.52
     listado
    -0.52
    es
    -0.52
    POSITIVE LOGITS
    InjectAttribute
    0.67
     gepubliceerd
    0.62
    httphttps
    0.62
    AddTagHelper
    0.57
    GraphicsUnit
    0.57
     Abonnez
    0.56
     pleaſure
    0.56
    OwnProperty
    0.54
    KURZBESCHREIBUNG
    0.54
     subsoil
    0.52
    Activations Density 0.083%

    No Known Activations