© 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. 3108
    Prev
    Next
    INDEX
    Explanations

    hila

    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
     itſelf
    -0.67
    <bos>
    -0.60
     Sarkozy
    -0.59
     faſt
    -0.58
     Huguen
    -0.58
     pleaſure
    -0.56
     Assy
    -0.55
     obſ
    -0.55
    PreExecute
    -0.55
     ſta
    -0.54
    POSITIVE LOGITS
    Datuak
    0.59
     préférence
    0.56
     gambe
    0.54
     Biôgrafia
    0.51
     prisonniers
    0.51
     preuves
    0.50
     africains
    0.50
     prochaines
    0.50
     geslacht
    0.48
     numéros
    0.48
    Activations Density 0.055%

    No Known Activations