© 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. 4551
    Prev
    Next
    INDEX
    Explanations

    Off

    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
    findpost
    -0.74
     springfox
    -0.73
    PageContext
    -0.73
    ftagPool
    -0.72
    HtmlAttribute
    -0.71
    })*/
    -0.70
    stateProvider
    -0.69
     noqa
    -0.69
     wheelchair
    -0.67
     Centa
    -0.66
    POSITIVE LOGITS
     otomatig
    0.47
    mergeFrom
    0.37
    MigrationBuilder
    0.35
     وتسجيلات
    0.30
    batore
    0.30
     Paglinawan
    0.29
    AppCompatTheme
    0.27
    itinéraire
    0.27
    aarrggbb
    0.25
    verläs
    0.25
    Activations Density 0.001%

    No Known Activations