© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73017
    Prev
    Next
    INDEX
    Explanations

    Web addresses, code

    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
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -1.09
    IntoConstraints
    -0.93
    Билгалдахарш
    -0.91
    NOPQRST
    -0.91
    rungsseite
    -0.90
     StatelessWidget
    -0.87
    queryInterface
    -0.84
    DockStyle
    -0.83
     InputDecoration
    -0.82
    AndEndTag
    -0.82
    POSITIVE LOGITS
    ad
    0.49
    pe
    0.44
    se
    0.42
    Pas
    0.42
    aps
    0.42
    pas
    0.40
    cap
    0.40
    Ad
    0.39
    more
    0.39
    vo
    0.39
    Activations Density 0.002%

    No Known Activations