© 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. 92343
    Prev
    Next
    INDEX
    Explanations

    of

    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
    StoryboardSegue
    -0.59
     referenties
    -0.57
     Numerade
    -0.56
    ์ตูน
    -0.56
     ddelweddau
    -0.54
    ***************/
    -0.51
     Marquette
    -0.50
     clearColor
    -0.50
     tampoco
    -0.49
    oltà
    -0.49
    POSITIVE LOGITS
    DockStyle
    0.74
    GOTREF
    0.69
    HomeAsUpEnabled
    0.57
    </thead>
    0.57
    auda
    0.57
    #![
    0.56
    Amicalement
    0.55
    INSTALLED
    0.54
    Cordialement
    0.53
    ThroughAttribute
    0.53
    Activations Density 0.158%

    No Known Activations