© 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. 6296
    Prev
    Next
    INDEX
    Explanations

    Start of text snippets

    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
    ponses
    -0.83
    rungsseite
    -0.60
    دانشنامهٔ
    -0.60
    تقاوى
    -0.56
    onomía
    -0.54
     ...'
    -0.54
    apollo
    -0.53
     Against
    -0.53
    ⁡
    -0.52
     cref
    -0.52
    POSITIVE LOGITS
    InitVars
    0.50
    uminense
    0.46
     betweenstory
    0.45
     Horizonte
    0.45
    itettura
    0.44
     Baillargeon
    0.44
     وتسجيلات
    0.43
    jectures
    0.43
    zeuge
    0.43
    renderItem
    0.43
    Activations Density 0.004%

    No Known Activations