© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43911
    Prev
    Next
    INDEX
    Explanations

    agree

    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
     agree
    -1.48
     deck
    -1.05
     agrees
    -1.03
    agree
    -0.90
     Agree
    -0.86
     Deck
    -0.85
    Deck
    -0.84
     agreeing
    -0.84
    Agree
    -0.77
     DECK
    -0.69
    POSITIVE LOGITS
    e
    0.65
    ership
    0.63
     betweenstory
    0.63
    ed
    0.61
    eer
    0.60
    er
    0.58
    ery
    0.57
    onOptions
    0.56
    able
    0.55
    quisition
    0.54
    Activations Density 1.363%

    No Known Activations