© 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. 71780
    Prev
    Next
    INDEX
    Explanations

    Technical/code documents

    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
    发表于
    -0.59
    UserScript
    -0.57
    кипедия
    -0.56
    COMES
    -0.55
     NIS
    -0.54
    WebServlet
    -0.53
     vatt
    -0.50
    ίδι
    -0.50
    ophilus
    -0.49
     elétrica
    -0.49
    POSITIVE LOGITS
     m
    0.57
    jsxFileName
    0.49
     Tor
    0.48
     Target
    0.48
     Allociné
    0.47
     esternos
    0.47
    Bakgrunnsstoff
    0.46
    createCanvas
    0.45
     TOR
    0.45
     AM
    0.44
    Activations Density 0.003%

    No Known Activations