© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40217
    Prev
    Next
    INDEX
    Explanations

    chemical reactions, geolocation

    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
     Reaction
    -1.18
    Reaction
    -1.13
    reaction
    -1.09
     reaction
    -1.08
     REACTION
    -1.02
     react
    -0.77
     Reactions
    -0.75
     реак
    -0.74
     reacting
    -0.73
     reactions
    -0.71
    POSITIVE LOGITS
    IsPostBack
    0.67
    ()?;
    0.59
    iség
    0.56
     ausged
    0.56
    hdys
    0.54
    Produkte
    0.53
    dispatchEvent
    0.52
     Molière
    0.52
    Carriera
    0.52
    UMBUS
    0.52
    Activations Density 0.032%

    No Known Activations