© 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. 1-CLT-HP
    7. 766
    Prev
    Next
    INDEX
    Explanations

    become

    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
     utafitiHapana
    -0.48
     épar
    -0.44
     devenus
    -0.43
     nueces
    -0.41
     resourceCulture
    -0.41
     wikipagina
    -0.39
     Superhosts
    -0.39
    DataAnnotations
    -0.39
     fallu
    -0.39
     CrossRef
    -0.38
    POSITIVE LOGITS
    SourceChecksum
    0.99
    AddTagHelper
    0.81
     betweenstory
    0.70
    IBOutlet
    0.66
     Meksiku
    0.66
     AssemblyCompany
    0.65
    Brainz
    0.65
     виправивши
    0.63
    Geplaatst
    0.63
    Zeneca
    0.63
    Activations Density 0.010%

    No Known Activations