© 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. 76578
    Prev
    Next
    INDEX
    Explanations

    scientific text

    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
     فريبيس
    -0.92
     autorytatywna
    -0.85
    存于互联网档案馆
    -0.79
    AnchorStyles
    -0.69
    ISupport
    -0.60
    Life
    -0.60
     AsyncTask
    -0.59
    ClientRect
    -0.58
    LIFE
    -0.57
     estekak
    -0.56
    POSITIVE LOGITS
    mannian
    0.45
     ThemeData
    0.45
    iture
    0.43
    ismuth
    0.41
    ichtung
    0.41
    힣
    0.40
    innung
    0.40
    牟
    0.39
    ith
    0.39
    CrossRef
    0.39
    Activations Density 0.005%

    No Known Activations