© 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. 0-CLT-HP
    7. 90533
    Prev
    Next
    INDEX
    Explanations

    aggregation

    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
     kaarangay
    -0.57
     automatiques
    -0.56
    Datuak
    -0.55
     peuples
    -0.54
    InitVars
    -0.54
    gatsby
    -0.54
     maquinaria
    -0.54
    iastes
    -0.54
    endrait
    -0.54
    kreis
    -0.53
    POSITIVE LOGITS
     determinations
    0.53
     accomplishment
    0.51
     Senza
    0.50
     itſelf
    0.50
     Theſe
    0.50
     uſe
    0.49
    хьтан
    0.49
     Manus
    0.49
    userdetails
    0.49
    \{\\
    0.48
    Activations Density 0.522%

    No Known Activations