© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42790
    Prev
    Next
    INDEX
    Explanations

    Code or Chinese

    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
    为
    -1.38
    為
    -1.38
     为
    -0.99
     為
    -0.94
    爲
    -0.79
     for
    -0.71
    为他
    -0.65
    为此
    -0.63
     для
    -0.61
    为自己
    -0.59
    POSITIVE LOGITS
    tanleria
    0.74
    SourceChecksum
    0.60
    findpost
    0.60
    ofollow
    0.58
    rzost
    0.57
    interopRequire
    0.57
     contextLoads
    0.56
    UnusedPrivate
    0.56
    )|^{
    0.55
    skrä
    0.54
    Activations Density 1.330%

    No Known Activations