© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 789
    Prev
    Next
    INDEX
    Explanations

    scientific texts

    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
    ParallelGroup
    -0.69
    DockStyle
    -0.64
     ProtoMessage
    -0.62
     typelib
    -0.58
    FormTagHelper
    -0.57
    TestBed
    -0.56
    addTab
    -0.55
    ButterKnife
    -0.55
    XmlAccessorType
    -0.54
    fork
    -0.54
    POSITIVE LOGITS
    makeText
    0.47
    TextInputLayout
    0.45
    Descarga
    0.43
    asanjo
    0.43
    saga
    0.43
     meras
    0.42
     Kristi
    0.41
    ünf
    0.40
     Sense
    0.40
     steg
    0.40
    Activations Density 0.014%

    No Known Activations