© 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. 5-CLT-HP
    7. 488
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
     Baillargeon
    -0.68
    invokeLater
    -0.54
    Manbalar
    -0.52
     biber
    -0.52
    ///
    -0.51
    numerusform
    -0.51
    CppMethod
    -0.51
    setVerticalGroup
    -0.50
     "}";
    -0.50
    iecie
    -0.50
    POSITIVE LOGITS
     فريبيس
    0.49
    MockMvc
    0.48
     OnInit
    0.48
     popularity
    0.48
    bootstrapcdn
    0.48
    AllowUser
    0.48
     счёт
    0.47
    SequentialGroup
    0.47
    seins
    0.47
     obro
    0.46
    Activations Density 0.002%

    No Known Activations