© 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. 91063
    Prev
    Next
    INDEX
    Explanations

    Technical/academic writing

    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
    Бахар
    -0.60
    IRQn
    -0.59
    ftagPool
    -0.54
    ündigung
    -0.53
    ,
    -0.52
    principalTable
    -0.52
    queryInterface
    -0.50
     parecia
    -0.49
    AndEndTag
    -0.48
    EndProject
    -0.48
    POSITIVE LOGITS
     myſelf
    0.60
    felves
    0.59
    ometers
    0.58
     חיצוניים
    0.58
    ESSOR
    0.57
    ſelves
    0.57
    TemporalType
    0.56
     Roskov
    0.54
     ſtand
    0.54
     ſmall
    0.54
    Activations Density 0.001%

    No Known Activations