© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 2893
    Prev
    Next
    INDEX
    Explanations

    the string " org" followed by a number

    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
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.17
     myſelf
    -1.05
     Monfieur
    -1.01
     pleaſure
    -0.88
     uſed
    -0.87
     ſtill
    -0.86
     raiſ
    -0.86
     Reſ
    -0.85
     faptul
    -0.84
     chofe
    -0.84
    POSITIVE LOGITS
     org
    1.68
     com
    0.87
     Org
    0.73
     ch
    0.54
     min
    0.54
     pic
    0.54
     sor
    0.53
     comp
    0.53
     por
    0.52
     app
    0.52
    Activations Density 0.028%

    No Known Activations