© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3361
    Prev
    Next
    INDEX
    Explanations

    or and

    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
    +:+
    -0.51
    %
    -0.50
     MenuView
    -0.48
     %
    -0.48
     springfox
    -0.46
     autorytatywna
    -0.45
     percent
    -0.44
    IEnumerator
    -0.43
    EReference
    -0.43
     esboço
    -0.42
    POSITIVE LOGITS
    levance
    0.64
     NDEBUG
    0.63
     XNUMX
    0.62
    sizeCache
    0.62
    zegor
    0.61
    ύπ
    0.59
     adjourn
    0.59
     adjournment
    0.59
     estimés
    0.59
    ziplin
    0.59
    Activations Density 0.004%

    No Known Activations