© 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. 5-CLT-HP
    7. 4601
    Prev
    Next
    INDEX
    Explanations

    which

    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
     '))
    -0.54
    )))));
    -0.53
    IsContent
    -0.51
    itarianism
    -0.51
     \%$\\
    -0.51
    pra
    -0.50
    Попис
    -0.49
     inizio
    -0.48
    hemia
    -0.48
     contextLoads
    -0.48
    POSITIVE LOGITS
    Rujuakan
    0.62
     sánh
    0.56
    Personensuche
    0.56
    Jeografia
    0.52
    NOPQRST
    0.52
    ArgsConstructor
    0.47
    endphp
    0.47
    iibo
    0.47
     to
    0.46
    korn
    0.46
    Activations Density 0.001%

    No Known Activations