© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74939
    Prev
    Next
    INDEX
    Explanations

    Technical language

    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
     pinulongan
    -0.54
    LEncoder
    -0.53
    ochim
    -0.49
    Kjelder
    -0.48
    Alike
    -0.48
    DockStyle
    -0.47
    AddHtmlAttribute
    -0.47
    Obrázky
    -0.47
    MigrationBuilder
    -0.46
    SPJ
    -0.45
    POSITIVE LOGITS
     TextInputType
    0.65
    úgó
    0.60
     dieux
    0.57
     AssemblyTitle
    0.56
    ?>">
    0.54
     hefyd
    0.53
    AxisAlignment
    0.53
    sizeCache
    0.52
    scriptcase
    0.52
    úsqueda
    0.51
    Activations Density 0.000%

    No Known Activations