© 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. 43121
    Prev
    Next
    INDEX
    Explanations

    patents

    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
    (
    -0.95
     Cluster
    -0.81
     miss
    -0.77
     patent
    -0.76
     cluster
    -0.72
    SourceChecksum
    -0.69
     AssemblyCulture
    -0.68
    XmlAccessorType
    -0.67
    ImageContext
    -0.67
    Referencie
    -0.66
    POSITIVE LOGITS
    ges
    0.55
    est
    0.53
    es
    0.52
    les
    0.52
    âl
    0.51
    po
    0.50
    fd
    0.49
    hip
    0.49
    OD
    0.48
    sie
    0.47
    Activations Density 0.196%

    No Known Activations