© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38434
    Prev
    Next
    INDEX
    Explanations

    proudly

    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
     proudly
    -0.70
    apimachinery
    -0.56
     kindly
    -0.53
     استنادى
    -0.51
    eder
    -0.51
    ed
    -0.50
    tagHelperRunner
    -0.49
    WebVitals
    -0.49
     Roskov
    -0.49
     alimentazione
    -0.48
    POSITIVE LOGITS
     doInBackground
    0.73
    DateField
    0.62
    lesque
    0.60
    rinfo
    0.59
     Armas
    0.58
    stro
    0.57
    cifix
    0.57
     <=",
    0.56
    archiviato
    0.56
     dama
    0.54
    Activations Density 0.122%

    No Known Activations