© 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. 1-CLT-HP
    7. 13365
    Prev
    Next
    INDEX
    Explanations

    kind

    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
     démocr
    -0.54
     antaranya
    -0.53
     procès
    -0.52
     cũng
    -0.50
     kecelakaan
    -0.49
     récents
    -0.49
    erráneo
    -0.49
     faciles
    -0.49
     ABOUT
    -0.49
     autorytatywna
    -0.49
    POSITIVE LOGITS
     برانيه
    0.62
    newArrayList
    0.59
    دانشنامهٔ
    0.58
     initComponents
    0.58
    uição
    0.56
     endregion
    0.56
     Efq
    0.54
    mishes
    0.54
     eleg
    0.54
    InjectMocks
    0.53
    Activations Density 0.011%

    No Known Activations