© 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. 1-CLT-HP
    7. 16008
    Prev
    Next
    INDEX
    Explanations

    world

    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
     igång
    -0.69
    @[+][
    -0.59
    WebVitals
    -0.58
    veien
    -0.58
    kranz
    -0.58
     administrativos
    -0.55
    Personensuche
    -0.55
     dapur
    -0.55
    Доставка
    -0.54
     egna
    -0.53
    POSITIVE LOGITS
    BeginContext
    0.63
    <bos>
    0.59
     Paglinawan
    0.55
     Precis
    0.54
    dafx
    0.54
     Obrador
    0.53
    PROTOBUF
    0.52
    Bibliograf
    0.52
    Jereo
    0.50
    MemoryWarning
    0.50
    Activations Density 0.007%

    No Known Activations