© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39790
    Prev
    Next
    INDEX
    Explanations

    cky

    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
    cky
    -1.13
     kel
    -0.88
    e
    -0.62
    y
    -0.62
    zkod
    -0.61
     ca
    -0.57
     la
    -0.54
    mast
    -0.53
    nagel
    -0.51
     Rubin
    -0.51
    POSITIVE LOGITS
    IsContent
    0.76
     itſelf
    0.75
     StatefulWidget
    0.66
    aarrggbb
    0.65
     myſelf
    0.64
    ſelves
    0.63
     ***!
    0.61
    .",
    
    0.60
     Efq
    0.59
    AccessorTable
    0.58
    Activations Density 0.118%

    No Known Activations