© 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. 4-CLT-HP
    7. 3035
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
    holding
    -0.65
     from
    -0.64
     newBuilder
    -0.63
     tearing
    -0.63
     TestBed
    -0.63
    from
    -0.62
    Holding
    -0.62
    showing
    -0.61
    talking
    -0.61
    ución
    -0.61
    POSITIVE LOGITS
     to
    0.62
    GraphicsUnit
    0.54
    ingtones
    0.49
     gain
    0.47
     never
    0.47
     return
    0.47
     pay
    0.46
     invest
    0.46
    InjectAttribute
    0.46
     witness
    0.45
    Activations Density 0.004%

    No Known Activations