© 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. 5-CLT-HP
    7. 92161
    Prev
    Next
    INDEX
    Explanations

    generation

    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
    InstanceState
    -0.62
     Picchu
    -0.59
    XmlAccessType
    -0.53
    consulté
    -0.53
     esternos
    -0.52
     ſtate
    -0.52
    utica
    -0.50
     pleaſure
    -0.50
     elétrica
    -0.49
    InvalidProtocol
    -0.48
    POSITIVE LOGITS
     gap
    0.84
    ally
    0.69
     Gap
    0.67
    gap
    0.64
    Gap
    0.62
    WithIOException
    0.60
    SHIP
    0.60
    ALLY
    0.59
     gaps
    0.59
    Predecesor
    0.55
    Activations Density 0.001%

    No Known Activations