© 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. 91216
    Prev
    Next
    INDEX
    Explanations

    academic references

    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
    InjectAttribute
    -0.87
    تقاوى
    -0.81
    LookAnd
    -0.79
     kaarangay
    -0.79
    tagHelperRunner
    -0.78
     AssemblyTitle
    -0.75
    IUrlHelper
    -0.73
     Мексичка
    -0.71
     transfieras
    -0.70
    GeoNames
    -0.70
    POSITIVE LOGITS
    .\\
    0.56
    दार
    0.51
    |}{}
    0.50
    entis
    0.49
     Febrero
    0.48
     \%$\\
    0.48
    urel
    0.47
     خلف
    0.47
     aang
    0.46
    qos
    0.46
    Activations Density 0.021%

    No Known Activations