© 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. 0-RES-MATRYOSHKA-DC
    7. 13582
    Prev
    Next
    INDEX
    Explanations

    the presence or absence of the word "is" in the document

    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
     itſelf
    -1.45
     Efq
    -1.34
     Jefus
    -1.28
     myſelf
    -1.27
     whoſe
    -1.24
     Monfieur
    -1.22
     purpoſe
    -1.21
     himſelf
    -1.18
     houſe
    -1.17
     Majefty
    -1.17
    POSITIVE LOGITS
    ↵↵
    0.57
     some
    0.56
    }
    0.55
    ,
    0.51
     Good
    0.50
     good
    0.49
    ]
    0.49
    ↵
    0.47
     
    0.47
     a
    0.46
    Activations Density 0.199%

    No Known Activations