© 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. 0-CLT-HP
    7. 97134
    Prev
    Next
    INDEX
    Explanations

    email updates/notifications

    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
     lenker
    -0.64
    SequentialGroup
    -0.63
     Credo
    -0.59
     Bagdad
    -0.57
    WithIOException
    -0.56
    ₁)
    -0.56
    θηκαν
    -0.56
     haup
    -0.55
    -/**
    -0.55
     Cairo
    -0.54
    POSITIVE LOGITS
     Using
    0.65
     rispar
    0.63
     This
    0.58
     spesa
    0.56
    Putting
    0.56
     Asking
    0.55
     trasmissione
    0.55
     Putting
    0.54
     utilizzando
    0.54
     The
    0.54
    Activations Density 0.018%

    No Known Activations