© 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. 92567
    Prev
    Next
    INDEX
    Explanations

    disulfide

    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
    WebServlet
    -0.67
     مرئيه
    -0.56
    JspWriter
    -0.55
    хьтан
    -0.54
     onPostExecute
    -0.53
     pulang
    -0.52
     typelib
    -0.51
     utafitiHapana
    -0.51
    canestro
    -0.49
    rawtypes
    -0.49
    POSITIVE LOGITS
     bridges
    0.79
     interchange
    0.74
     bridge
    0.71
     bond
    0.71
     bonds
    0.66
    brücken
    0.62
     exchange
    0.60
     Interchange
    0.60
     Bridges
    0.59
    Bridges
    0.58
    Activations Density 0.002%

    No Known Activations