© 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. 20-CLT-HP
    7. 75582
    Prev
    Next
    INDEX
    Explanations

    PO

    np_max-act-logits · 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
    migrationBuilder
    -0.66
     سكانية
    -0.66
    endphp
    -0.51
     Roskov
    -0.51
    webElementXpaths
    -0.50
    InitVars
    -0.49
    Бахар
    -0.48
     lenker
    -0.47
     scarpe
    -0.47
     AssemblyTitle
    -0.46
    POSITIVE LOGITS
    ########.
    0.54
    pagno
    0.54
    Sucesor
    0.53
     विश्वसनीयता
    0.52
    +#+
    0.49
    ergies
    0.48
    \"");
    0.48
    IVAS
    0.47
     defStyle
    0.46
    alade
    0.45
    Activations Density 0.001%

    No Known Activations