© 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. 5-CLT-HP
    7. 96
    Prev
    Next
    INDEX
    Explanations

    responsibility disclaimers

    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
    exitRule
    -0.52
    kloped
    -0.50
    ganan
    -0.49
    StreetMap
    -0.47
     recensement
    -0.47
    GeneratedMessage
    -0.47
    yntaxException
    -0.47
     ecce
    -0.47
     Réponses
    -0.47
    ngua
    -0.46
    POSITIVE LOGITS
    новништво
    0.65
    jera
    0.57
     jScrollPane
    0.52
     content
    0.49
     initComponents
    0.48
     DIGITAL
    0.47
    oraf
    0.47
     pressing
    0.47
    ADATA
    0.47
    CAPÍTULO
    0.46
    Activations Density 0.020%

    No Known Activations