© 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. 91032
    Prev
    Next
    INDEX
    Explanations

    be

    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
    yntaxException
    -0.71
    лтамалар
    -0.57
    ScopeManager
    -0.52
    RegressionTest
    -0.49
     немає
    -0.49
     scolaires
    -0.49
     nessuno
    -0.48
    kháu
    -0.48
     grève
    -0.47
    Демографія
    -0.47
    POSITIVE LOGITS
    ernalia
    0.60
     &___
    0.59
     admin
    0.54
     at
    0.54
     Admin
    0.54
     كومونز
    0.54
    Sklici
    0.53
    WAUKEE
    0.52
    ajas
    0.52
     ]]
    0.52
    Activations Density 0.011%

    No Known Activations