© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4108
    Prev
    Next
    INDEX
    Explanations

    hand

    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
     noqa
    -0.59
    __':
    -0.58
    urlpatterns
    -0.57
    ByPrimaryKey
    -0.54
    __':
    -0.53
    OrBuilder
    -0.52
    ForKey
    -0.50
     ब्रेकडाउन
    -0.50
    henko
    -0.49
    DispatchToProps
    -0.49
    POSITIVE LOGITS
     himſelf
    0.61
     greateſt
    0.55
     poffe
    0.50
     leaſt
    0.50
     Chriſt
    0.50
     myſelf
    0.50
     ſeveral
    0.49
     ſtate
    0.48
     imprimer
    0.48
     whoſe
    0.47
    Activations Density 0.011%

    No Known Activations