© 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. 90860
    Prev
    Next
    INDEX
    Explanations

    location names

    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
    verwijspagina
    -0.71
     disambiguazione
    -0.68
    لينكات
    -0.67
    </tfoot>
    -0.66
    Sklici
    -0.66
    tvguidetime
    -0.65
     للمعارف
    -0.64
    ніципалі
    -0.62
    хьтан
    -0.61
     EconPapers
    -0.60
    POSITIVE LOGITS
     Michael
    0.53
     totem
    0.49
     Martin
    0.49
     feo
    0.48
     Totem
    0.47
     Miche
    0.47
    DetailComponent
    0.46
     Edson
    0.45
    Martin
    0.44
    Michael
    0.44
    Activations Density 0.005%

    No Known Activations