© 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. 1-CLT-HP
    7. 9057
    Prev
    Next
    INDEX
    Explanations

    context

    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
    ting
    -0.60
    Javadoc
    -0.59
    ted
    -0.57
    PYX
    -0.55
    AYO
    -0.54
    tedt
    -0.53
    UseVisualStyle
    -0.53
     it
    -0.52
    webElementXpaths
    -0.52
     U
    -0.51
    POSITIVE LOGITS
     Ciro
    0.66
     vastaan
    0.63
    StoryboardSegue
    0.60
     mukana
    0.58
     Pareto
    0.57
     ESF
    0.57
     Giuliano
    0.57
     whofe
    0.55
    marshaller
    0.55
     tdci
    0.54
    Activations Density 0.020%

    No Known Activations