© 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. 5842
    Prev
    Next
    INDEX
    Explanations

    differences and variations

    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
     fråga
    -0.75
     pytanie
    -0.73
     dépens
    -0.57
     réfugiés
    -0.56
     modalités
    -0.55
     clue
    -0.54
     kérdés
    -0.54
     probleem
    -0.52
    phism
    -0.52
     везе
    -0.52
    POSITIVE LOGITS
     videos
    0.88
     articles
    0.86
     pinulongan
    0.81
     stories
    0.81
     تضيفلها
    0.77
     pieces
    0.71
     poems
    0.69
     examples
    0.69
     texts
    0.68
     statements
    0.68
    Activations Density 0.005%

    No Known Activations