© 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. 71393
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
    webElement
    -0.58
    CopyWith
    -0.51
     mé
    -0.49
    shr
    -0.49
    💼
    -0.47
    windowFixed
    -0.46
    олові
    -0.46
    QMetaType
    -0.45
    XmlAccessType
    -0.44
     BEAR
    -0.44
    POSITIVE LOGITS
    Obrázky
    0.75
    InjectAttribute
    0.68
    onAttach
    0.63
    WebServlet
    0.63
    misión
    0.55
    Pozri
    0.55
    opia
    0.55
    setopt
    0.54
     Serviço
    0.54
    WaitGroup
    0.53
    Activations Density 0.006%

    No Known Activations