© 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. 4681
    Prev
    Next
    INDEX
    Explanations

    technical/system logs and code

    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
     StatefulWidget
    -0.63
     الرياضيه
    -0.57
    protoimpl
    -0.52
     TestBed
    -0.51
    SourceChecksum
    -0.48
    createCell
    -0.46
    وصلات
    -0.46
    amal
    -0.45
    Ế
    -0.45
    Enlaces
    -0.45
    POSITIVE LOGITS
    DebuggerNonUser
    0.59
    Portail
    0.59
    titleMargin
    0.55
    nop
    0.51
    hogs
    0.48
     soggiorno
    0.48
    hog
    0.48
     võib
    0.48
    OURCE
    0.48
    jaw
    0.48
    Activations Density 0.002%

    No Known Activations