© 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. 1-CLT-HP
    7. 15911
    Prev
    Next
    INDEX
    Explanations

    meat

    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
     betweenstory
    -0.49
     NgModule
    -0.48
     Cascades
    -0.48
    loem
    -0.46
    inaires
    -0.45
    
    -0.45
     locker
    -0.45
    ImageContext
    -0.44
    θρώ
    -0.44
    merkung
    -0.43
    POSITIVE LOGITS
     BoxDecoration
    0.75
    SourceChecksum
    0.65
    ViewFeatures
    0.57
     ویکی‌پدیا
    0.55
     conjuncti
    0.54
    ReusableCell
    0.53
     pylint
    0.52
    JNIEnv
    0.51
    insegna
    0.50
    хьтан
    0.49
    Activations Density 0.011%

    No Known Activations