© 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. 0-CLT-HP
    7. 43793
    Prev
    Next
    INDEX
    Explanations

    verification and origin

    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
     downstream
    -0.81
     upstream
    -0.79
     authentic
    -0.77
    authentic
    -0.74
    upstream
    -0.71
     authentique
    -0.65
     authenticity
    -0.65
    djangoproject
    -0.63
    Authentic
    -0.61
    AddTagHelper
    -0.61
    POSITIVE LOGITS
    er
    0.74
    ally
    0.73
    ness
    0.71
    ening
    0.71
    ly
    0.69
    ers
    0.68
    ating
    0.68
    ity
    0.65
    s
    0.64
    ting
    0.63
    Activations Density 0.069%

    No Known Activations