© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73398
    Prev
    Next
    INDEX
    Explanations

    ranges and limits

    np_max-act-logits · 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
    TagMode
    -0.47
     Q
    -0.43
     Stadium
    -0.40
    HideFlags
    -0.40
     House
    -0.39
    Q
    -0.39
    chting
    -0.39
     marchandises
    -0.39
     Saint
    -0.39
     Day
    -0.38
    POSITIVE LOGITS
    \{\\
    0.61
    EndProject
    0.60
     vapors
    0.59
     CWE
    0.57
     bows
    0.57
     useAppContext
    0.57
     mV
    0.56
    flows
    0.55
    openConnection
    0.55
    !*\
    0.54
    Activations Density 0.005%

    No Known Activations