© 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. 1-CLT-HP
    7. 13652
    Prev
    Next
    INDEX
    Explanations

    end

    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
    graded
    -0.52
     padd
    -0.49
     Wilbur
    -0.49
    OrEqual
    -0.49
     hitch
    -0.49
    nastics
    -0.49
     woof
    -0.48
     ending
    -0.48
    Rés
    -0.47
     wineries
    -0.47
    POSITIVE LOGITS
    ocardio
    0.64
     intptr
    0.62
    ovascular
    0.61
    opath
    0.54
    abetes
    0.52
    ocarditis
    0.50
     esterni
    0.47
    featureID
    0.47
    oves
    0.46
    otherapy
    0.46
    Activations Density 0.101%

    No Known Activations