© 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. 2947
    Prev
    Next
    INDEX
    Explanations

    of

    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
     TestBed
    -0.57
    :{
    -0.56
     ModelRenderer
    -0.49
    といけない
    -0.49
     the
    -0.48
    :✨
    -0.47
    :}
    -0.47
     للمعارف
    -0.46
     pinulongan
    -0.46
     EconPapers
    -0.45
    POSITIVE LOGITS
     
    1.09
    VersionUID
    0.69
     XNUMX
    0.65
     sixty
    0.63
     thousands
    0.63
     numberOfRows
    0.63
     eighty
    0.61
     fifty
    0.60
     seventy
    0.60
     twenty
    0.59
    Activations Density 0.041%

    No Known Activations