© 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. 75906
    Prev
    Next
    INDEX
    Explanations

    {# the

    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
    saraba
    -0.63
     سكانية
    -0.57
     Efq
    -0.56
     ∙
    -0.56
     Biôgrafia
    -0.52
    Enllaces
    -0.51
     NavController
    -0.51
     Rine
    -0.48
     Esq
    -0.48
     oleo
    -0.48
    POSITIVE LOGITS
     chi
    0.55
    شاف
    0.49
    CHI
    0.48
    outSlope
    0.47
    migrationBuilder
    0.47
    InitStruct
    0.47
    interopRequire
    0.46
    encodeWith
    0.45
    FilterChain
    0.45
    UBA
    0.45
    Activations Density 0.006%

    No Known Activations