© 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. 0-CLT-HP
    7. 40356
    Prev
    Next
    INDEX
    Explanations

    viruses

    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
    virus
    -1.59
    viruses
    -1.34
    Virus
    -0.91
    viral
    -0.87
     Efq
    -0.77
     ions
    -0.76
    erapeu
    -0.75
     Virus
    -0.75
    ^(@)
    -0.75
    Brainz
    -0.74
    POSITIVE LOGITS
    ES
    0.51
    esta
    0.51
    es
    0.49
    ers
    0.48
    est
    0.47
    ERS
    0.47
    EST
    0.45
    ة
    0.43
    NES
    0.41
    多
    0.41
    Activations Density 0.355%

    No Known Activations