© 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. 97494
    Prev
    Next
    INDEX
    Explanations

    titles or legal documents

    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
    -1.09
     ―――――
    -1.05
     itſelf
    -1.03
     Monfieur
    -0.99
     Houſe
    -0.94
     Majefty
    -0.93
     Efq
    -0.93
    ſelf
    -0.93
     Jefus
    -0.91
    ſelves
    -0.88
    POSITIVE LOGITS
    lesias
    0.57
     Le
    0.51
    -
    0.48
    ы
    0.47
    :
    0.47
     "
    0.47
     target
    0.47
    ->
    0.46
    il
    0.45
     H
    0.45
    Activations Density 0.073%

    No Known Activations