© 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. 93619
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    oient
    -0.52
     Địa
    -0.52
    hematical
    -0.52
     tín
    -0.51
    veau
    -0.48
    adeloupe
    -0.48
     Aufs
    -0.47
     مؤرشف
    -0.47
    riet
    -0.46
     مشين
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.64
     BoxDecoration
    0.63
     Highness
    0.61
     Roskov
    0.61
    Искәрмәләр
    0.60
     geslacht
    0.59
     EconPapers
    0.59
     AssemblyTitle
    0.57
     GenerationType
    0.57
     JADX
    0.54
    Activations Density 0.003%

    No Known Activations