© 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. 97196
    Prev
    Next
    INDEX
    Explanations

    readable text

    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
     spikes
    -0.96
     fluctuations
    -0.84
     spike
    -0.82
     fluctuation
    -0.80
     Read
    -0.74
     pointed
    -0.73
     spiked
    -0.73
    spikes
    -0.71
    adpleegd
    -0.70
     projection
    -0.69
    POSITIVE LOGITS
    ober
    0.55
     hash
    0.52
    hash
    0.50
    angi
    0.50
    ']],
    0.48
     thủ
    0.47
    localScale
    0.47
     second
    0.46
    val
    0.45
    ui
    0.45
    Activations Density 0.736%

    No Known Activations