© 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. 97048
    Prev
    Next
    INDEX
    Explanations

    worry, hurt

    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
    once
    -1.26
     once
    -1.23
     Once
    -1.13
    Once
    -1.11
    ONCE
    -1.07
     ONCE
    -1.04
     worry
    -0.92
     anxiety
    -0.89
    worry
    -0.89
     Worry
    -0.88
    POSITIVE LOGITS
    writeFieldEnd
    0.61
    tanleria
    0.59
    ,:]
    0.53
     indietro
    0.53
     zwaar
    0.51
     îna
    0.49
    PyExc
    0.49
    Ligações
    0.48
    ocuk
    0.47
     approached
    0.46
    Activations Density 0.116%

    No Known Activations