© 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. 1-CLT-HP
    7. 12187
    Prev
    Next
    INDEX
    Explanations

    bur

    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
     bur
    -0.91
     burs
    -0.77
     Burs
    -0.70
    bur
    -0.69
     estimés
    -0.63
    MethodManager
    -0.51
    usepackage
    -0.51
     Roles
    -0.50
    Normdaten
    -0.50
    <?
    -0.50
    POSITIVE LOGITS
    nable
    0.50
    Cyfarwyddwr
    0.50
    iap
    0.49
     revanche
    0.48
    autique
    0.48
    ValueGeneration
    0.48
    sui
    0.48
    sitis
    0.47
    aság
    0.45
    apur
    0.45
    Activations Density 0.056%

    No Known Activations