© 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. 4-CLT-HP
    7. 3329
    Prev
    Next
    INDEX
    Explanations

    adverbs

    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
     myſelf
    -0.82
     متعلقه
    -0.77
     Monfieur
    -0.74
    hasMoreElements
    -0.71
     ſeveral
    -0.70
    findpost
    -0.70
     Majefty
    -0.70
    Життєпис
    -0.68
    存于互联网档案馆
    -0.68
    Personensuche
    -0.66
    POSITIVE LOGITS
     covered
    0.45
     accepted
    0.43
     defined
    0.43
    nese
    0.42
    OfMonth
    0.41
     '
    0.41
     "
    0.40
     appreciated
    0.40
    STA
    0.39
     recognized
    0.38
    Activations Density 0.003%

    No Known Activations