© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45589
    Prev
    Next
    INDEX
    Explanations

    ts

    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
    rand
    -0.47
    親
    -0.43
     menj
    -0.43
    ण्ड
    -0.42
    tées
    -0.42
    artige
    -0.41
    httphttps
    -0.41
     mein
    -0.41
    jed
    -0.41
    s
    -0.39
    POSITIVE LOGITS
    iastes
    0.66
    TestingModule
    0.66
    DATABASES
    0.62
     "..\..\..\
    0.62
    endphp
    0.62
    Xiv
    0.61
    Последние
    0.59
    CppMethod
    0.59
    GraphicsUnit
    0.59
     Мексичка
    0.58
    Activations Density 0.008%

    No Known Activations