© 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. 2428
    Prev
    Next
    INDEX
    Explanations

    the word "third" or the phrase "third party"

    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
    th
    -0.71
     th
    -0.63
    enei
    -0.63
    WaitGroup
    -0.63
     Presley
    -0.60
     Cortes
    -0.57
    DispatchToProps
    -0.55
     SX
    -0.52
    DOCTYPE
    -0.51
    ukah
    -0.51
    POSITIVE LOGITS
    Third
    1.73
     third
    1.59
    third
    1.59
     Third
    1.55
    THIRD
    1.43
     THIRD
    1.42
     Thirdly
    1.21
    第三
    1.09
     thirds
    1.04
     tercero
    1.04
    Activations Density 0.072%

    No Known Activations