© 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. 5-CLT-HP
    7. 97061
    Prev
    Next
    INDEX
    Explanations

    detecting any text

    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
    AndEndTag
    -0.90
    VIAF
    -0.83
     AssemblyCompany
    -0.71
    Демографія
    -0.69
    Jeografia
    -0.68
    ServletException
    -0.67
    >{@
    -0.67
    saurus
    -0.66
     Biôgrafia
    -0.66
    ViewFeatures
    -0.64
    POSITIVE LOGITS
     the
    0.71
    Према
    0.46
     body
    0.45
    rofoam
    0.42
    kadi
    0.40
    ghen
    0.39
    分け
    0.39
    setContentView
    0.38
    noc
    0.38
    expandindo
    0.38
    Activations Density 0.001%

    No Known Activations