© 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. 4-CLT-HP
    7. 2631
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
     GenerationType
    -0.49
     to
    -0.47
     and
    -0.44
    ,
    -0.43
     skr
    -0.42
     (
    -0.42
    findpost
    -0.41
     living
    -0.41
     FOX
    -0.40
     binding
    -0.40
    POSITIVE LOGITS
    脚注の使い方
    0.80
     سكانية
    0.78
    dafx
    0.69
     NUKAT
    0.69
     InputDecoration
    0.68
    Geplaatst
    0.68
    jalá
    0.68
    ImageContext
    0.68
     sumpay
    0.66
     want
    0.66
    Activations Density 0.016%

    No Known Activations