© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42421
    Prev
    Next
    INDEX
    Explanations

    procedures or systems

    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
     process
    -1.01
    process
    -0.88
     Process
    -0.82
    Process
    -0.80
     proceso
    -0.61
     PROCESS
    -0.61
     proses
    -0.58
    PROCESS
    -0.56
     procesos
    -0.56
     processus
    -0.55
    POSITIVE LOGITS
     Efq
    1.14
     Jefus
    1.09
     purpoſe
    1.05
     ſche
    1.03
     myſelf
    1.02
     ་་
    0.98
     Shakspeare
    0.93
     Cæsar
    0.91
     Chriftian
    0.91
     itſelf
    0.90
    Activations Density 0.195%

    No Known Activations