© 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. 91222
    Prev
    Next
    INDEX
    Explanations

    academic papers

    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
     تضيفلها
    -0.71
     calendriers
    -0.67
    SpringBootTest
    -0.61
     JpaRepository
    -0.59
     مشين
    -0.57
    lably
    -0.57
     ['./
    -0.56
    complexContent
    -0.56
    TableBody
    -0.55
    AGES
    -0.55
    POSITIVE LOGITS
     voraus
    0.52
     rencontr
    0.49
    🇮
    0.48
    ',
    0.48
     tratto
    0.47
    ungguhnya
    0.47
    tvguidetime
    0.46
     gezicht
    0.45
    jspx
    0.45
     geschlossen
    0.44
    Activations Density 0.029%

    No Known Activations