© 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. 72948
    Prev
    Next
    INDEX
    Explanations

    Names 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
     Paglinawan
    -0.45
    %@",
    -0.43
    ősz
    -0.42
     Outre
    -0.42
    rawdę
    -0.42
     ooh
    -0.41
    ächlich
    -0.41
    nanoTime
    -0.40
    Doh
    -0.40
    -</
    -0.39
    POSITIVE LOGITS
    featureID
    0.81
    brido
    0.64
    sizeCache
    0.62
     mergeFrom
    0.60
    parsedMessage
    0.60
     >=",
    0.59
     []:
    0.57
     viewDidLoad
    0.56
     Kepler
    0.55
    TestingModule
    0.55
    Activations Density 0.000%

    No Known Activations