© 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. 12095
    Prev
    Next
    INDEX
    Explanations

    pay

    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
     '\\;'
    -0.66
    WebVitals
    -0.61
    contentLoaded
    -0.55
    Pay
    -0.54
     paid
    -0.51
    Cyfeiriadau
    -0.50
     selling
    -0.49
     {}));
    -0.49
    astéro
    -0.48
    ftagPool
    -0.48
    POSITIVE LOGITS
    osoba
    0.52
     PopupWindow
    0.50
    ganet
    0.50
    displayquote
    0.49
    idered
    0.49
    NIP
    0.49
    ようになって
    0.49
    jiri
    0.49
     Hip
    0.47
    apter
    0.46
    Activations Density 0.007%

    No Known Activations