© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97803
    Prev
    Next
    INDEX
    Explanations

    varied text sources

    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
     maternelle
    -0.57
     Huguen
    -0.54
    abestanden
    -0.54
    IntoConstraints
    -0.54
     kasarigan
    -0.51
     democrática
    -0.51
    readystatechange
    -0.50
    AndEndTag
    -0.49
     sortes
    -0.48
    >",
    -0.48
    POSITIVE LOGITS
    Portail
    0.68
    windowFixed
    0.67
     وتسجيلات
    0.59
    تفصیلات
    0.56
    InjectAttribute
    0.54
    DockStyle
    0.53
     Wicidata
    0.51
     Inn
    0.49
    SqlSession
    0.49
    tellbar
    0.47
    Activations Density 0.000%

    No Known Activations