© 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. 71739
    Prev
    Next
    INDEX
    Explanations

    a

    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
    Izvori
    -0.75
     InputDecoration
    -0.66
     ligiloj
    -0.66
    منابع
    -0.65
     فريبيس
    -0.64
    Referências
    -0.63
    arXiv
    -0.63
    UserScript
    -0.61
    Références
    -0.61
     ujednoznacz
    -0.59
    POSITIVE LOGITS
     l
    0.47
     betweenstory
    0.45
     mirror
    0.43
    getCmp
    0.38
    rotto
    0.37
    modb
    0.37
     AssemblyProduct
    0.36
     view
    0.36
    ellt
    0.35
    awtextra
    0.35
    Activations Density 0.000%

    No Known Activations