© 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. 5-CLT-HP
    7. 5028
    Prev
    Next
    INDEX
    Explanations

    cid

    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
     للاسماء
    -0.92
    ViewImports
    -0.71
     Normdatei
    -0.70
    UIControlState
    -0.67
    MemoryWarning
    -0.61
    adpleegd
    -0.60
    المناصب
    -0.58
    UpInside
    -0.58
     ddelweddau
    -0.57
     NSCoder
    -0.57
    POSITIVE LOGITS
     télé
    0.55
    gawai
    0.46
     Pey
    0.46
     Col
    0.44
    selen
    0.44
     col
    0.44
    HttpFoundation
    0.44
    naden
    0.43
    newswire
    0.43
    Col
    0.43
    Activations Density 0.002%

    No Known Activations