© 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. 2679
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    DoubleQuotes
    -0.76
    ToBounds
    -0.67
    BufferException
    -0.65
     oysters
    -0.63
     defStyleAttr
    -0.62
    Waters
    -0.60
     eels
    -0.59
    principles
    -0.59
     Rains
    -0.58
     MainAxisSize
    -0.58
    POSITIVE LOGITS
    principalColumn
    0.49
    ngOnInit
    0.44
    先代
    0.44
     obstante
    0.43
    forChild
    0.42
    AnchorTagHelper
    0.41
    IConfiguration
    0.41
    chequer
    0.40
     vendar
    0.40
     Republic
    0.40
    Activations Density 0.003%

    No Known Activations