© 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. 40540
    Prev
    Next
    INDEX
    Explanations

    Launching

    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
     launching
    -0.65
    ThroughAttribute
    -0.57
     di
    -0.55
     launch
    -0.55
    iyi
    -0.52
     thy
    -0.52
     setuptools
    -0.52
    itoneal
    -0.50
    chio
    -0.49
    iya
    -0.48
    POSITIVE LOGITS
     >=",
    0.85
     houſe
    0.80
     ſever
    0.79
     himſelf
    0.78
     itſelf
    0.77
     ſmall
    0.77
     purpoſe
    0.76
     CreateTagHelper
    0.75
     greateſt
    0.75
     raiſ
    0.75
    Activations Density 0.239%

    No Known Activations