© 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. 43613
    Prev
    Next
    INDEX
    Explanations

    content

    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
     Content
    -0.62
    AttributeSet
    -0.53
     CreateTagHelper
    -0.52
    DialogContent
    -0.50
    Content
    -0.50
     ing
    -0.50
    utz
    -0.49
    — 
    -0.49
     externi
    -0.49
    рез
    -0.48
    POSITIVE LOGITS
     itſelf
    0.82
     myſelf
    0.80
     himſelf
    0.79
     Monfieur
    0.78
     Jefus
    0.78
     themſelves
    0.76
    ^(@)
    0.71
     Anſ
    0.70
    tagext
    0.69
     Houſe
    0.68
    Activations Density 0.211%

    No Known Activations