© 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. 5-CLT-HP
    7. 95071
    Prev
    Next
    INDEX
    Explanations

    and

    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
    Билгалдахарш
    -0.73
     initComponents
    -0.71
    })$}
    -0.66
    '))
    -0.64
    SuppressLint
    -0.64
    AutoScaleMode
    -0.62
     ")");
    -0.62
    StartCoroutine
    -0.61
     الاطلاع
    -0.61
     Normdatei
    -0.61
    POSITIVE LOGITS
     intptr
    0.54
     morena
    0.43
     webdriver
    0.41
    tabular
    0.41
     peggio
    0.40
    出版年
    0.40
    انه
    0.40
    ({
    0.39
     hydrauli
    0.39
     fata
    0.39
    Activations Density 0.002%

    No Known Activations