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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96622
    Prev
    Next
    INDEX
    Explanations

    references to the past

    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
     given
    -0.53
     that
    -0.47
     now
    -0.46
     or
    -0.45
     seen
    -0.45
     
    -0.44
     future
    -0.44
    IsInitialized
    -0.44
     previously
    -0.44
     pro
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    0.73
    ChildScrollView
    0.70
     colectiva
    0.68
    הערות
    0.67
    ButterKnife
    0.65
     pleaſure
    0.65
     ſeveral
    0.64
    شهاد
    0.62
    ſelf
    0.61
    cipar
    0.60
    Activations Density 0.002%

    No Known Activations