© 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. 94138
    Prev
    Next
    INDEX
    Explanations

    Background/Indoor

    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
     background
    -2.25
     Background
    -2.03
     backgrounds
    -1.99
    background
    -1.97
    Background
    -1.88
     BACKGROUND
    -1.76
    BACKGROUND
    -1.60
    背景
    -1.42
     Hintergrund
    -1.42
     backdrop
    -1.38
    POSITIVE LOGITS
     الحره
    0.72
    s
    0.67
     Meilleur
    0.63
     Certo
    0.62
    AntiForgeryToken
    0.61
    AddTagHelper
    0.60
    ſelf
    0.59
    ContentAlignment
    0.59
    nefs
    0.57
    Abitanti
    0.54
    Activations Density 0.425%

    No Known Activations