© 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. 4706
    Prev
    Next
    INDEX
    Explanations

    diagrams and schematics

    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
     arrep
    -0.56
     tranquille
    -0.52
     malheure
    -0.50
     progresso
    -0.50
     jaunes
    -0.49
     generales
    -0.49
     vidas
    -0.49
     decorazione
    -0.47
     dår
    -0.47
     razon
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.77
    <bos>
    0.75
    riwal
    0.72
    ernalia
    0.66
    setupUi
    0.65
    gameserver
    0.65
    getItemId
    0.65
    AccessorTable
    0.64
    bosis
    0.63
    CloseOperation
    0.63
    Activations Density 0.010%

    No Known Activations