Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74369
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     snippetHide
    -0.79
    WebMethod
    -0.77
    principalTable
    -0.76
    GEBURTSDATUM
    -0.74
    LabelTagHelper
    -0.72
    OnAdd
    -0.71
    ThroughAttribute
    -0.71
    BeginInit
    -0.70
    tagHelperRunner
    -0.68
    ngdoc
    -0.68
    POSITIVE LOGITS
    verwijspagina
    0.48
     un
    0.47
    amna
    0.42
    Fig
    0.41
     Fig
    0.41
     une
    0.41
     Dor
    0.40
    rungsseite
    0.39
    setzt
    0.38
     thank
    0.38
    Activations Density 0.010%

    No Known Activations