© 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. 93243
    Prev
    Next
    INDEX
    Explanations

    infection

    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
    AsUp
    -0.74
    WebVitals
    -0.73
    EndContext
    -0.68
    awtextra
    -0.64
    ParallelGroup
    -0.63
     дописавши
    -0.63
     protoimpl
    -0.59
    ardom
    -0.59
    tagHelperRunner
    -0.58
    MLLoader
    -0.58
    POSITIVE LOGITS
     dead
    0.64
    dead
    0.56
     sufferers
    0.53
    Dead
    0.51
     insects
    0.51
     Taus
    0.49
     Dead
    0.49
    DEAD
    0.49
     lifeless
    0.49
     DEAD
    0.48
    Activations Density 0.001%

    No Known Activations