© 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. 90952
    Prev
    Next
    INDEX
    Explanations

    phased

    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
     consent
    -0.67
     phased
    -0.65
     consents
    -0.65
     Consent
    -0.62
     cycles
    -0.61
     phasing
    -0.60
    HomeAsUpEnabled
    -0.59
    ///</
    -0.58
     للاسماء
    -0.58
    Pozri
    -0.57
    POSITIVE LOGITS
    parsedMessage
    0.62
     arraigned
    0.53
     '{@
    0.52
    a
    0.52
    setVerticalGroup
    0.52
    ProcessEvent
    0.51
     Herzens
    0.49
    olia
    0.49
    étoit
    0.48
    /*---
    0.48
    Activations Density 0.084%

    No Known Activations