© 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. 1-CLT-HP
    7. 936
    Prev
    Next
    INDEX
    Explanations

    names

    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
    ThroughAttribute
    -0.74
    sizeCache
    -0.73
    makeText
    -0.71
    Hauptartikel
    -0.69
    Portail
    -0.69
    
    -0.68
     مشين
    -0.66
    EDEFAULT
    -0.66
    tagHelperRunner
    -0.65
    Források
    -0.65
    POSITIVE LOGITS
     Sidd
    0.43
     Majest
    0.42
    ніципа
    0.41
    Solic
    0.41
     laun
    0.40
    cce
    0.40
    StateList
    0.39
    segue
    0.39
    signee
    0.39
     accla
    0.39
    Activations Density 0.073%

    No Known Activations