© 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. 1-CLT-HP
    7. 14872
    Prev
    Next
    INDEX
    Explanations

    Variety

    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
    umab
    -0.58
    unittest
    -0.57
    modb
    -0.57
    المكان
    -0.57
    engager
    -0.56
     épu
    -0.56
     extérieurs
    -0.56
     mijne
    -0.55
     tjen
    -0.54
    AndroidJUnit
    -0.54
    POSITIVE LOGITS
     propOrder
    0.56
    rowa
    0.53
    restling
    0.48
     Himo
    0.47
    zarchiwizowane
    0.45
     magasiner
    0.45
    DDG
    0.44
    τός
    0.44
     tang
    0.44
    fowl
    0.43
    Activations Density 0.006%

    No Known Activations