© 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. 0-CLT-HP
    7. 39983
    Prev
    Next
    INDEX
    Explanations

    bring

    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
     Bring
    -1.07
    Bring
    -0.96
    bring
    -0.87
     bring
    -0.81
     brings
    -0.68
     Brings
    -0.65
     BRING
    -0.62
     Turn
    -0.53
     k
    -0.52
     pro
    -0.52
    POSITIVE LOGITS
    wiſe
    0.64
     Serikat
    0.63
    Hochspringen
    0.62
     gangen
    0.59
     leaſt
    0.58
    MENAFN
    0.57
    (;;)
    0.57
     Inſ
    0.57
    backing
    0.56
     torno
    0.56
    Activations Density 1.564%

    No Known Activations