© 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. 94433
    Prev
    Next
    INDEX
    Explanations

    hand

    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
    LookAnd
    -0.68
     vecka
    -0.65
    setupUi
    -0.60
     stället
    -0.60
     мәкал
    -0.57
     skrevet
    -0.55
     möjlighet
    -0.54
    SourceChecksum
    -0.54
     vanligt
    -0.51
    Revenir
    -0.51
    POSITIVE LOGITS
     you
    0.74
     we
    0.69
    __*/
    0.65
    CloseOperation
    0.55
    <?>>
    0.54
    InstanceState
    0.52
    atisfaction
    0.51
    嬉しいです
    0.50
    iencies
    0.50
     الحره
    0.50
    Activations Density 0.003%

    No Known Activations