© 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. 20-CLT-HP
    7. 71645
    Prev
    Next
    INDEX
    Explanations

    code terms

    np_max-act-logits · 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
    ius
    -0.59
     centrifugal
    -0.46
    عة
    -0.46
     AnyObject
    -0.45
    yearly
    -0.44
    bele
    -0.44
     allergic
    -0.44
    clusion
    -0.43
     gæ
    -0.43
    zyden
    -0.43
    POSITIVE LOGITS
     intptr
    0.95
    ValueStyle
    0.70
    awtextra
    0.70
     NSCoder
    0.69
    ScopeManager
    0.66
    StoryboardSegue
    0.64
     oprot
    0.63
    WebElementEntity
    0.61
    tagHelperRunner
    0.59
    DockStyle
    0.59
    Activations Density 0.000%

    No Known Activations