Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44621
    Prev
    Next
    INDEX
    Explanations

    ae

    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
    s
    -0.78
    serv
    -0.72
    sen
    -0.70
    ness
    -0.68
    share
    -0.67
    tin
    -0.65
    ing
    -0.65
    song
    -0.64
    t
    -0.64
     gang
    -0.63
    POSITIVE LOGITS
     raiſ
    0.79
     myſelf
    0.76
     Monfieur
    0.73
     оригіналу
    0.72
     '\\;'
    0.70
     uſed
    0.69
    +#+#
    0.68
     autorytatywna
    0.67
     الحره
    0.67
    ItemBackground
    0.66
    Activations Density 1.366%

    No Known Activations