© 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. 4-CLT-HP
    7. 879
    Prev
    Next
    INDEX
    Explanations

    Perspectives and methods

    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
     '
    -0.49
     ‘
    -0.46
     per
    -0.43
     de
    -0.43
    ly
    -0.43
     a
    -0.43
     "
    -0.41
    ity
    -0.41
     single
    -0.41
     fast
    -0.40
    POSITIVE LOGITS
    findpost
    1.12
    sidemargin
    0.96
    ViewImports
    0.93
     GenerationType
    0.88
     שוליים
    0.86
     referenties
    0.80
    بوابة
    0.80
    HostException
    0.79
    OCCURRED
    0.79
     CreateTagHelper
    0.79
    Activations Density 0.001%

    No Known Activations