© 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. 94338
    Prev
    Next
    INDEX
    Explanations

    technical/license text

    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
     fact
    -0.57
    fact
    -0.55
    paedia
    -0.55
    rizona
    -0.53
    alised
    -0.53
     ویکی‌پدیا
    -0.52
    دانشنامهٔ
    -0.50
    ówki
    -0.49
    atown
    -0.49
    KURZBESCHREIBUNG
    -0.48
    POSITIVE LOGITS
    บัติ
    0.57
     Nons
    0.57
     confirmé
    0.52
    ✨:
    0.51
     initComponents
    0.51
    toMatch
    0.51
     of
    0.49
    外部链接
    0.49
     Grazie
    0.49
     intptr
    0.48
    Activations Density 1.609%

    No Known Activations