© 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. 5-CLT-HP
    7. 5336
    Prev
    Next
    INDEX
    Explanations

    selection

    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
    '])){
    -0.56
    camore
    -0.48
     ")[
    -0.47
    Linki
    -0.47
    ()])
    -0.47
    aringan
    -0.46
     Roskov
    -0.46
    themselves
    -0.45
     CURIAM
    -0.45
    Referencies
    -0.45
    POSITIVE LOGITS
    Filmografie
    0.73
     WaitForSeconds
    0.71
    setViewportView
    0.68
     >=",
    0.65
     getItemId
    0.59
    piac
    0.59
     Magellan
    0.56
     IndexPath
    0.56
     propOrder
    0.55
     Vesti
    0.53
    Activations Density 0.005%

    No Known Activations