© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38535
    Prev
    Next
    INDEX
    Explanations

    scared

    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
    fear
    -1.76
     fear
    -1.70
     fearful
    -1.68
     scared
    -1.67
     frightened
    -1.63
     terrified
    -1.60
     peur
    -1.56
    scared
    -1.55
     scares
    -1.52
     afraid
    -1.52
    POSITIVE LOGITS
     of
    0.96
     in
    0.82
    ,
    0.71
     for
    0.69
     and
    0.67
     over
    0.66
     as
    0.65
     not
    0.62
    .
    0.61
    ↵
    0.59
    Activations Density 0.082%

    No Known Activations