© 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. 5-CLT-HP
    7. 3844
    Prev
    Next
    INDEX
    Explanations

    informational texts

    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
     recently
    -1.01
     yesterday
    -1.01
     lately
    -0.98
    recently
    -0.94
    yesterday
    -0.93
    rawDesc
    -0.91
     tomorrow
    -0.89
     Yesterday
    -0.88
     now
    -0.84
    ьаж
    -0.83
    POSITIVE LOGITS
     فريبيس
    0.54
     atunci
    0.53
    当时的
    0.48
     ziua
    0.47
     BorderRadius
    0.46
     při
    0.46
     dumne
    0.46
     piele
    0.45
     viață
    0.45
    foglio
    0.44
    Activations Density 0.037%

    No Known Activations