© 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. 0-CLT-HP
    7. 93747
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    queryInterface
    -0.78
     itſelf
    -0.68
     ſtate
    -0.66
     ſche
    -0.65
     ſch
    -0.64
     myſelf
    -0.64
     purpoſe
    -0.63
     Chriftian
    -0.63
    anyahu
    -0.62
     arisen
    -0.61
    POSITIVE LOGITS
    ed
    0.49
    Manbalar
    0.48
    Linki
    0.48
     désolés
    0.47
    Kjelder
    0.47
    Atsauces
    0.47
    Referências
    0.47
    GOTREF
    0.47
    frain
    0.46
    ⓧ
    0.46
    Activations Density 0.071%

    No Known Activations