© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1405
    Prev
    Next
    INDEX
    Explanations

    Code/legal document

    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
     betweenstory
    -0.84
    ReusableCell
    -0.76
    ContentAsync
    -0.75
    WriteTagHelper
    -0.72
     BoxFit
    -0.71
     StringTokenizer
    -0.69
     AssemblyVersion
    -0.68
     nawr
    -0.65
    IntoConstraints
    -0.65
     Վերցված
    -0.64
    POSITIVE LOGITS
    is
    0.69
    to
    0.69
    if
    0.62
    i
    0.59
    has
    0.57
    will
    0.54
    in
    0.51
    ive
    0.51
    does
    0.50
    goes
    0.50
    Activations Density 0.018%

    No Known Activations