© 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. 95485
    Prev
    Next
    INDEX
    Explanations

    risks and rewards

    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
     "..\..\
    -0.56
    maßen
    -0.50
     varandra
    -0.49
     őket
    -0.48
     efficaces
    -0.47
    cellaneous
    -0.46
     rağmen
    -0.45
    กัน
    -0.45
     confiance
    -0.45
     pouvoit
    -0.45
    POSITIVE LOGITS
     of
    1.52
     posed
    0.75
    InjectAttribute
    0.68
     curve
    0.65
    of
    0.65
    ของ
    0.65
     imposed
    0.64
    XmlAccessType
    0.62
     của
    0.61
     difference
    0.61
    Activations Density 0.091%

    No Known Activations