© 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. 4-CLT-HP
    7. 2104
    Prev
    Next
    INDEX
    Explanations

    including

    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
    HasAnnotation
    -0.51
    ckså
    -0.49
    ویری
    -0.49
    ⚭
    -0.49
    ButterKnife
    -0.49
     ilmo
    -0.48
    minimalist
    -0.47
    opedia
    -0.47
    InstrumentedTest
    -0.47
    ản
    -0.47
    POSITIVE LOGITS
     affecting
    0.64
     producing
    0.63
    enumii
    0.60
     up
    0.60
    writeField
    0.59
     disrupting
    0.59
     approximately
    0.58
     importing
    0.58
     about
    0.57
     billions
    0.57
    Activations Density 0.002%

    No Known Activations