© 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. 1-CLT-HP
    7. 838
    Prev
    Next
    INDEX
    Explanations

    Suffixes

    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
    Referințe
    -0.68
    istry
    -0.66
     snippetHide
    -0.58
    complexContent
    -0.57
     kasarigan
    -0.56
    وروبا
    -0.54
    qrstuvwxyz
    -0.54
     Normdatei
    -0.52
    gridy
    -0.52
    sizeCache
    -0.52
    POSITIVE LOGITS
    SourceChecksum
    0.51
    migrationBuilder
    0.51
    msgTypes
    0.48
     bek
    0.47
    ",&
    0.46
     nguyên
    0.45
     Variant
    0.45
    anwal
    0.45
    roxene
    0.44
     самому
    0.44
    Activations Density 0.260%

    No Known Activations