© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 90988
    Prev
    Next
    INDEX
    Explanations

    sequence/progression

    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
    Negative Logits
     defaultstate
    -0.55
     requests
    -0.51
    szönöm
    -0.49
     optimally
    -0.48
    properly
    -0.47
    risse
    -0.47
    requests
    -0.47
    Sklici
    -0.46
     dimaksud
    -0.45
    SerializedSize
    -0.45
    POSITIVE LOGITS
    ftagPool
    0.58
    +#+#
    0.57
    RegressionTest
    0.54
    تقاوى
    0.52
    Vee
    0.52
     Roskov
    0.51
     see
    0.51
     مشين
    0.50
     famí
    0.49
     Fø
    0.48
    Activations Density 0.001%

    No Known Activations