© 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. 20-CLT-HP
    7. 74720
    Prev
    Next
    INDEX
    Explanations

    Apple products and apps

    np_max-act-logits · 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
    oredCriteria
    -0.71
     '\\;'
    -0.69
    出版年
    -0.69
    BufferException
    -0.67
    ukone
    -0.67
     martyrdom
    -0.63
     ardu
    -0.63
     Kicks
    -0.62
     gyhoeddwyd
    -0.62
    dolu
    -0.62
    POSITIVE LOGITS
    ,‎
    0.46
     IP
    0.43
    IP
    0.42
    I
    0.39
     I
    0.38
    App
    0.36
     olla
    0.35
    New
    0.35
    first
    0.34
     Mall
    0.34
    Activations Density 0.002%

    No Known Activations