© 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. 1-CLT-HP
    7. 15501
    Prev
    Next
    INDEX
    Explanations

    research

    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
    APORE
    -0.66
     autorytatywna
    -0.66
    Programme
    -0.63
     Programme
    -0.63
     snippetHide
    -0.61
     PROGRAMME
    -0.61
    FormTagHelper
    -0.59
    MigrationBuilder
    -0.59
     createState
    -0.58
    DispatchToProps
    -0.57
    POSITIVE LOGITS
     NATURAL
    0.46
     Natural
    0.46
     jsPsych
    0.46
    Natural
    0.44
    lais
    0.41
     springfox
    0.41
    ئيس
    0.40
     natural
    0.40
    bParam
    0.40
    InstrumentedTest
    0.39
    Activations Density 0.014%

    No Known Activations