© 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. 20-CLT-HP
    7. 76374
    Prev
    Next
    INDEX
    Explanations

    Numbers and code

    np_max-act-logits · 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
     &___
    -0.64
    findpost
    -0.58
    sizeCache
    -0.50
    /**
    -0.49
    ьаж
    -0.49
     lørdag
    -0.48
    xase
    -0.48
    KommentareTeilen
    -0.48
    utnik
    -0.48
    ⁹
    -0.48
    POSITIVE LOGITS
    matite
    0.52
     متعلقه
    0.49
     mouseY
    0.45
     vanille
    0.45
    utilisons
    0.45
    хьтан
    0.44
    為に
    0.44
    simas
    0.44
    uarine
    0.44
    bean
    0.44
    Activations Density 0.001%

    No Known Activations