© 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. 45538
    Prev
    Next
    INDEX
    Explanations

    Money/finance

    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
     myſelf
    -1.41
     Monfieur
    -1.39
     itſelf
    -1.38
     Majefty
    -1.36
     pleaſure
    -1.34
     Jefus
    -1.33
    ſelf
    -1.30
     houſe
    -1.30
     Houſe
    -1.27
    ſelves
    -1.26
    POSITIVE LOGITS
     =
    0.62
    gh
    0.61
    .
    0.59
    al
    0.58
    h
    0.58
    ,
    0.56
     -
    0.55
    B
    0.55
    he
    0.54
    ere
    0.54
    Activations Density 0.030%

    No Known Activations