© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97718
    Prev
    Next
    INDEX
    Explanations

    el

    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
    InjectAttribute
    -0.78
     незавершена
    -0.73
    SPATH
    -0.66
    <bos>
    -0.65
    SPJ
    -0.63
    GIH
    -0.57
     MyBatis
    -0.57
    expandindo
    -0.56
     aberration
    -0.56
    存于互联网档案馆
    -0.55
    POSITIVE LOGITS
    FormTagHelper
    0.57
     queuing
    0.52
     lining
    0.52
     stocking
    0.48
    ientôt
    0.47
     safer
    0.47
    úsqueda
    0.46
    vstack
    0.46
    робнее
    0.45
     testing
    0.45
    Activations Density 0.001%

    No Known Activations