© 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. 93459
    Prev
    Next
    INDEX
    Explanations

    trade

    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
     Signalez
    -0.56
    espère
    -0.54
    RenderAtEndOf
    -0.53
     bezeichneter
    -0.52
     }</
    -0.52
     الحره
    -0.52
     ویکی‌آمباردا
    -0.49
     myſelf
    -0.49
    SaveVideo
    -0.49
    istisches
    -0.49
    POSITIVE LOGITS
    off
    0.70
    wind
    0.61
    OFF
    0.60
    offs
    0.59
    away
    0.51
     متعلقه
    0.51
    ormick
    0.51
    antMatchers
    0.51
     Rout
    0.50
    break
    0.50
    Activations Density 0.002%

    No Known Activations