© 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. 97865
    Prev
    Next
    INDEX
    Explanations

    code licenses and playing

    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
    resave
    -0.55
     Biophys
    -0.42
     Dred
    -0.41
    numerusform
    -0.40
     hundred
    -0.40
     externi
    -0.40
     Golgi
    -0.39
     kasarigan
    -0.38
    róleo
    -0.37
     widened
    -0.37
    POSITIVE LOGITS
     autorytatywna
    0.77
    出版年
    0.71
    feinander
    0.65
     igång
    0.64
    ρκ
    0.59
    tanooga
    0.56
     resourceCulture
    0.55
    Controllo
    0.55
     '{@
    0.54
    CppCodeGen
    0.53
    Activations Density 0.002%

    No Known Activations