© 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. 0-CLT-HP
    7. 94731
    Prev
    Next
    INDEX
    Explanations

    night

    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
     فريبيس
    -1.11
    DockStyle
    -1.03
    HasAnnotation
    -0.96
    InputBorder
    -0.93
    AddTagHelper
    -0.87
    TagMode
    -0.87
     للمعارف
    -0.85
     تانيه
    -0.84
    IntoConstraints
    -0.84
    EndProject
    -0.83
    POSITIVE LOGITS
     the
    0.57
    ↵↵
    0.51
    .
    0.50
     );
    0.48
    ,
    0.46
     i
    0.44
     
    0.44
    ky
    0.43
    *)&
    0.43
     some
    0.42
    Activations Density 0.121%

    No Known Activations