© 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. 0-CLT-HP
    7. 95058
    Prev
    Next
    INDEX
    Explanations

    activity

    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
     activity
    -1.13
     activities
    -1.10
    activities
    -1.04
    Activities
    -1.02
    Activity
    -1.01
     Activity
    -0.99
    activity
    -0.98
     Aktivität
    -0.97
     aktivitet
    -0.97
     Activities
    -0.95
    POSITIVE LOGITS
    s
    0.58
    ы
    0.50
    sink
    0.45
    @{
    0.45
     ni
    0.43
     “
    0.42
     mit
    0.42
     tor
    0.41
     Should
    0.41
     for
    0.40
    Activations Density 1.065%

    No Known Activations