© 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. 2028
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ArrowToggle
    -0.86
     autorytatywna
    -0.68
     BoxFit
    -0.66
    SpringBootTest
    -0.60
    CopyWith
    -0.60
    ніципалі
    -0.59
    AccessorTable
    -0.58
    DockStyle
    -0.58
    rungsseite
    -0.57
    ]--;
    -0.57
    POSITIVE LOGITS
    openzeppelin
    0.51
    Intial
    0.50
    ódz
    0.48
    zerne
    0.47
    <![
    0.47
     daß
    0.46
     breath
    0.45
    Transkript
    0.45
    Décès
    0.44
    نیم
    0.44
    Activations Density 0.001%

    No Known Activations