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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93678
    Prev
    Next
    INDEX
    Explanations

    alternating current

    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
     activate
    -1.27
     alternating
    -1.25
     activated
    -1.24
     activates
    -1.21
     activating
    -1.20
     activation
    -1.19
     alternate
    -1.06
    activated
    -1.02
     activists
    -1.02
     Activate
    -1.02
    POSITIVE LOGITS
    NOPQRST
    0.55
     BorderRadius
    0.49
    ating
    0.46
    DoubleQuotes
    0.45
     InputDecoration
    0.45
    ates
    0.44
     tartalomajánló
    0.43
     kaynağından
    0.42
    ृत
    0.42
    ^^^^^^^^
    0.42
    Activations Density 0.092%

    No Known Activations