© 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. 90875
    Prev
    Next
    INDEX
    Explanations

    Is

    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
     Majefty
    -0.68
     Cæsar
    -0.61
    mine
    -0.59
    cised
    -0.58
     mennes
    -0.58
     purpoſe
    -0.57
     quæ
    -0.57
     memberId
    -0.56
     equiv
    -0.56
     superflu
    -0.56
    POSITIVE LOGITS
    DrawerToggle
    0.65
     ***!
    0.62
    CodeAttribute
    0.57
    aarrggbb
    0.57
     kaynağından
    0.56
     发表于
    0.54
    AddTagHelper
    0.53
    QMetaType
    0.51
    '}>
    0.50
     WaitForSeconds
    0.49
    Activations Density 0.002%

    No Known Activations