© 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. 2-RES-MATRYOSHKA-DC
    7. 4106
    Prev
    Next
    INDEX
    Explanations

    references to the word "with" or similar expressions indicating inclusion or association

    oai_token-act-pair · gpt-4.1-nano
    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
     JpaRepository
    -0.58
    Obrázky
    -0.57
    XmlAccessType
    -0.57
     ostavi
    -0.55
    bitField
    -0.52
    MessageOf
    -0.50
    AddHtmlAttribute
    -0.49
    parsedMessage
    -0.48
    listFiles
    -0.48
    VersionUID
    -0.47
    POSITIVE LOGITS
     With
    1.70
    With
    1.64
    WITH
    1.30
     WITH
    1.19
     Avec
    1.05
     Dengan
    0.96
    Dengan
    0.89
    Avec
    0.88
     Without
    0.83
    Without
    0.80
    Activations Density 0.071%

    No Known Activations