© 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. 4373
    Prev
    Next
    INDEX
    Explanations

    AIDS/HIV

    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
    ImageContext
    -0.85
    Portail
    -0.79
    aarrggbb
    -0.76
     EconPapers
    -0.74
    principalTable
    -0.67
    expandindo
    -0.65
    libft
    -0.63
    Personensuche
    -0.62
     виправивши
    -0.61
     nakalista
    -0.61
    POSITIVE LOGITS
    steamcommunity
    0.49
     lade
    0.46
    wb
    0.43
    ingway
    0.42
    databinding
    0.41
     DIEGO
    0.41
    ENIX
    0.40
     zit
    0.40
    philips
    0.40
    ]")]
    0.40
    Activations Density 0.002%

    No Known Activations