© 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. 4-CLT-HP
    7. 1677
    Prev
    Next
    INDEX
    Explanations

    describes results

    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
    Probably
    -0.62
    probably
    -0.61
    
    -0.61
    GEBURTSDATUM
    -0.60
     initComponents
    -0.60
     probablemente
    -0.59
    AsUp
    -0.58
    instead
    -0.57
     replaceable
    -0.57
     suffit
    -0.56
    POSITIVE LOGITS
     فريبيس
    0.63
    writeFieldEnd
    0.48
    OGND
    0.48
    ,
    0.47
    CompoundButton
    0.47
    chyma
    0.47
    יקה
    0.46
     onOptions
    0.46
    kloped
    0.46
     ahor
    0.45
    Activations Density 0.002%

    No Known Activations