© 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. 92651
    Prev
    Next
    INDEX
    Explanations

    main

    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
     CreateTagHelper
    -0.85
    Enllaces
    -0.81
     betweenstory
    -0.79
     تضيفلها
    -0.77
    ########.
    -0.75
    KommentareTeilen
    -0.71
    Lähteet
    -0.71
     समीक्षाओं
    -0.71
    WithIOException
    -0.70
    homonymie
    -0.69
    POSITIVE LOGITS
     planning
    0.47
     decision
    0.44
     long
    0.43
     control
    0.42
     point
    0.42
     source
    0.42
     policy
    0.41
    GINIA
    0.40
    +#+
    0.40
     œufs
    0.40
    Activations Density 0.006%

    No Known Activations