© 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. 4-CLT-HP
    7. 3007
    Prev
    Next
    INDEX
    Explanations

    research

    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
    inians
    -0.45
     "
    -0.39
    一个是
    -0.38
    ÁS
    -0.37
    LLES
    -0.37
     direct
    -0.36
     honor
    -0.35
     du
    -0.35
     large
    -0.35
     j
    -0.34
    POSITIVE LOGITS
     Efq
    1.02
     Мексичка
    0.90
    ArgsConstructor
    0.90
     itſelf
    0.89
     étoit
    0.88
     ainfi
    0.86
     auroit
    0.82
    HomeAsUpEnabled
    0.82
     Shakspeare
    0.80
     Chriftian
    0.79
    Activations Density 0.141%

    No Known Activations