Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1318
    Prev
    Next
    INDEX
    Explanations

    forth

    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
    хьтан
    -0.68
    ształ
    -0.60
    CompilerServices
    -0.57
     ComVisible
    -0.55
    reportWebVitals
    -0.55
    classmethod
    -0.54
    getOutputStream
    -0.54
    ۇ
    -0.53
    )]=
    -0.53
    الصفحه
    -0.53
    POSITIVE LOGITS
     keskus
    0.62
    transQ
    0.57
     familiale
    0.53
     المعيارى
    0.52
     of
    0.50
    principalTable
    0.49
     banter
    0.48
     culturale
    0.47
     siitä
    0.46
    ribusi
    0.46
    Activations Density 0.001%

    No Known Activations