© 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. 78109
    Prev
    Next
    INDEX
    Explanations

    technical web snippets

    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
    Negative Logits
     Pristupljeno
    -0.63
    /**
    -0.62
     BorderRadius
    -0.60
    MessageTagHelper
    -0.56
     <>",
    -0.55
    elemField
    -0.55
     onCancelled
    -0.54
    PerformLayout
    -0.53
    IVEREF
    -0.52
    bolista
    -0.51
    POSITIVE LOGITS
    yscale
    0.53
    ox
    0.52
     referrerpolicy
    0.52
     Luxe
    0.49
    UnusedPrivate
    0.48
     parche
    0.47
     Model
    0.47
    ửa
    0.47
    UCIÓN
    0.47
     duquel
    0.46
    Activations Density 0.002%

    No Known Activations