© 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. 2807
    Prev
    Next
    INDEX
    Explanations

    structure

    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
     handleMessage
    -0.61
    허
    -0.52
    MENAFN
    -0.51
    djangoproject
    -0.48
     kasarigan
    -0.47
    Trả
    -0.47
     sô
    -0.46
    amoja
    -0.46
    ربای
    -0.46
    iprot
    -0.46
    POSITIVE LOGITS
     SIMBAD
    0.58
    ScopeManager
    0.55
    Демографія
    0.54
     متعلقه
    0.54
    windowFixed
    0.54
    ecd
    0.53
     LD
    0.52
     виправивши
    0.52
    InitVars
    0.52
    
    0.52
    Activations Density 0.003%

    No Known Activations