© 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. 43722
    Prev
    Next
    INDEX
    Explanations

    ability

    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
     Bring
    -0.52
    balleur
    -0.52
     Bringing
    -0.50
    onics
    -0.50
    orist
    -0.50
     Wicidata
    -0.49
     dép
    -0.49
    cagon
    -0.48
    Bringing
    -0.48
    ak
    -0.48
    POSITIVE LOGITS
     protoimpl
    0.68
    AsUp
    0.64
    DIPSETTING
    0.63
     utafitiHapana
    0.61
    Tembelea
    0.61
    RegressionTest
    0.60
    مراجع
    0.60
    CppCodeGen
    0.59
    Xna
    0.56
    حوالہ
    0.56
    Activations Density 0.391%

    No Known Activations