© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 1470
    Prev
    Next
    INDEX
    Explanations

    the words "enable" and "disable".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     كومونز
    -0.93
     votos
    -0.78
    MemoryWarning
    -0.77
     الحره
    -0.76
     DMT
    -0.75
     odkazy
    -0.74
     useRef
    -0.74
     CreateTagHelper
    -0.73
     polaire
    -0.73
     محفوظة
    -0.72
    POSITIVE LOGITS
     enable
    1.58
     Enable
    1.56
     ENABLE
    1.54
     enabled
    1.48
    enabled
    1.45
    ENABLE
    1.43
    Enable
    1.42
    enable
    1.41
     Enabled
    1.41
    ENABLED
    1.33
    Activations Density 0.194%

    No Known Activations