© 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. 4-CLT-HP
    7. 2824
    Prev
    Next
    INDEX
    Explanations

    maximum

    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
     nahilalakip
    -0.82
     utafitiHapana
    -0.82
     NgModule
    -0.81
     AssemblyProduct
    -0.80
     pinulongan
    -0.79
    tvguidetime
    -0.79
    رشف
    -0.73
     فريبيس
    -0.69
     otomatig
    -0.69
    évaluateur
    -0.68
    POSITIVE LOGITS
     values
    0.51
    جوايز
    0.44
     temperature
    0.42
    values
    0.42
     that
    0.42
     temperatures
    0.41
    RemoteException
    0.41
    ona
    0.40
    temper
    0.39
    JoinColumn
    0.39
    Activations Density 0.003%

    No Known Activations