© 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. 6046
    Prev
    Next
    INDEX
    Explanations

    subsets

    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
    InjectAttribute
    -0.61
     subset
    -0.56
    pirable
    -0.54
     vérit
    -0.51
     básicos
    -0.50
    UrlResolution
    -0.50
     tertentu
    -0.50
    ]')
    -0.49
    ftagPool
    -0.48
     extré
    -0.48
    POSITIVE LOGITS
     bands
    0.59
    ніципалі
    0.57
    BufferException
    0.55
    obel
    0.50
     GAP
    0.49
     gardeners
    0.48
     Equi
    0.48
     Worth
    0.48
     Tower
    0.48
     trails
    0.48
    Activations Density 0.009%

    No Known Activations