© 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. 4702
    Prev
    Next
    INDEX
    Explanations

    writing and academic texts

    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
     محفوظة
    -0.60
    titleMargin
    -0.58
     lautet
    -0.52
     ladri
    -0.51
    évaluateur
    -0.51
    óstico
    -0.49
     استنادى
    -0.49
     विश्वसनीयता
    -0.49
    ÍTULO
    -0.48
    pecia
    -0.47
    POSITIVE LOGITS
     doing
    0.74
     DOING
    0.70
    GraphicsUnit
    0.70
     registering
    0.63
     inhabiting
    0.63
     multiplying
    0.62
     documenting
    0.62
     resolving
    0.60
     lining
    0.60
     controlling
    0.60
    Activations Density 0.000%

    No Known Activations