© 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. 38936
    Prev
    Next
    INDEX
    Explanations

    argued

    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
    GEBURTS
    -0.79
    OGND
    -0.78
     виправивши
    -0.77
    تقاوى
    -0.75
    Билгалдахарш
    -0.72
     autorytatywna
    -0.70
    expandindo
    -0.66
    ंदीखरीदारी
    -0.64
     utafitiHapana
    -0.63
    ?\\
    -0.62
    POSITIVE LOGITS
    <bos>
    0.58
    horabuena
    0.58
     extensively
    0.58
     paljon
    0.56
     frequently
    0.51
     notoriously
    0.50
     purported
    0.50
    ̍
    0.49
     widely
    0.48
     anzunehmen
    0.48
    Activations Density 0.123%

    No Known Activations