© 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. 5-CLT-HP
    7. 92333
    Prev
    Next
    INDEX
    Explanations

    view

    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
     nakalista
    -0.73
    GraphicsUnit
    -0.65
    ArgsConstructor
    -0.57
    Hochspringen
    -0.54
    expandindo
    -0.52
    onghi
    -0.52
     ExecuteAsync
    -0.52
    numerusform
    -0.51
    Przypisy
    -0.50
    Redacción
    -0.48
    POSITIVE LOGITS
     kasarigan
    0.91
    ObjectContext
    0.64
     AppComponent
    0.64
     Encyclopædia
    0.62
    ImageField
    0.59
    KeySpec
    0.57
     ainfi
    0.56
     bordir
    0.56
     épaules
    0.55
     invités
    0.54
    Activations Density 0.001%

    No Known Activations