© 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. 95418
    Prev
    Next
    INDEX
    Explanations

    andre

    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
    andre
    -1.38
    ANDRE
    -0.64
    scriptcase
    -0.63
    principalTable
    -0.57
    ANDA
    -0.56
    andro
    -0.53
    anda
    -0.51
     defaultstate
    -0.51
    DllImport
    -0.50
    ствий
    -0.50
    POSITIVE LOGITS
    ("]");
    0.63
     *)__
    0.62
     betweenstory
    0.61
    ))^{
    0.61
    ftagPool
    0.57
    jspx
    0.57
    SOUNDBITE
    0.56
    HideFlags
    0.56
     Commencez
    0.55
    UserScript
    0.55
    Activations Density 0.108%

    No Known Activations