© 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. 5-CLT-HP
    7. 475
    Prev
    Next
    INDEX
    Explanations

    specific times and dates

    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
    tagHelperRunner
    -0.65
     :
    -0.60
    contentLoaded
    -0.56
    Marks
    -0.56
    ArgsConstructor
    -0.53
    abestanden
    -0.53
     betweenstory
    -0.51
     iſt
    -0.50
    Turns
    -0.49
    $​
    -0.48
    POSITIVE LOGITS
    tvguidetime
    0.52
    GRANTED
    0.52
     везе
    0.50
    مراجع
    0.50
    fusc
    0.49
     omissions
    0.49
    ngx
    0.48
    ivores
    0.48
    tanleria
    0.48
    клопе
    0.48
    Activations Density 0.012%

    No Known Activations