© 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. 6076
    Prev
    Next
    INDEX
    Explanations

    best

    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
     дописавши
    -0.74
    PerformLayout
    -0.62
    richTextPanel
    -0.61
     mergeFrom
    -0.59
    ✨:
    -0.57
     ElementRef
    -0.57
     Biôgrafia
    -0.56
    })()
    -0.55
     rhestr
    -0.54
    Personensuche
    -0.54
    POSITIVE LOGITS
     bet
    0.60
     opportunity
    0.53
     case
    0.50
     possible
    0.49
     men
    0.46
     trương
    0.46
     wager
    0.45
    原始内容存档于
    0.45
     path
    0.44
    strum
    0.44
    Activations Density 0.002%

    No Known Activations