© 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. 72311
    Prev
    Next
    INDEX
    Explanations

    Code and text mixture

    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
    ItemBackground
    -0.87
    Portail
    -0.81
    SharedCtor
    -0.75
     lenker
    -0.73
    ագրություններ
    -0.70
     surla
    -0.69
    ValueStyle
    -0.69
     الرخصة
    -0.69
    DebuggerNonUser
    -0.68
    MemoryWarning
    -0.67
    POSITIVE LOGITS
    quelize
    0.49
    ówno
    0.42
     Breslau
    0.40
    >(),
    0.39
     fft
    0.37
    fgets
    0.37
     Dollar
    0.37
     Ascot
    0.37
     Tatar
    0.36
     owl
    0.36
    Activations Density 0.001%

    No Known Activations