© 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. 90994
    Prev
    Next
    INDEX
    Explanations

    Technical words

    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
    aways
    -0.59
    存于互联网档案馆
    -0.57
     المعيارى
    -0.57
    Ladd
    -0.55
    HasForeignKey
    -0.55
    ufig
    -0.52
     Cancelar
    -0.52
    ⓧ
    -0.51
    HtmlAttribute
    -0.50
    giver
    -0.50
    POSITIVE LOGITS
     AssemblyCompany
    0.67
    ]';
    0.54
    ">—
    0.52
    ,:),
    0.51
    Portail
    0.51
    巯
    0.50
    ())))
    0.50
    MLLoader
    0.49
    BeginInit
    0.48
     DataTypes
    0.47
    Activations Density 0.003%

    No Known Activations