© 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. 0-CLT-HP
    7. 94574
    Prev
    Next
    INDEX
    Explanations

    time/sequence/quantity

    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
    nt
    -0.71
    ents
    -0.64
    last
    -0.56
    mm
    -0.54
    ism
    -0.52
    cing
    -0.50
    ds
    -0.49
    Last
    -0.48
    hers
    -0.48
    ward
    -0.47
    POSITIVE LOGITS
    ViewFeatures
    0.84
     Мексичка
    0.83
    IUrlHelper
    0.83
    tvguidetime
    0.82
     ProtoMessage
    0.77
    ]),
    0.74
    رشف
    0.72
    ReusableCell
    0.71
    #
    0.69
    queryInterface
    0.69
    Activations Density 0.235%

    No Known Activations