© 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. 0-CLT-HP
    7. 38832
    Prev
    Next
    INDEX
    Explanations

    vernacular

    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
     guard
    -0.49
    ύ
    -0.45
     condition
    -0.44
     guards
    -0.40
     Guards
    -0.40
     Westminster
    -0.39
    ira
    -0.38
    др
    -0.37
    cetin
    -0.37
     Oscar
    -0.37
    POSITIVE LOGITS
    seamnă
    0.85
    s
    0.78
     виправивши
    0.77
    Geplaatst
    0.73
    følgelig
    0.73
    DockStyle
    0.72
     дописавши
    0.71
    ؤلاء
    0.70
    tanleria
    0.68
    ship
    0.67
    Activations Density 1.590%

    No Known Activations