© 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. 3493
    Prev
    Next
    INDEX
    Explanations

    references to professional writers or the concept of being a writer

    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
     Authority
    -0.57
     Carefully
    -0.54
    ุณ
    -0.54
     fiche
    -0.54
    read
    -0.53
    Read
    -0.52
    änder
    -0.52
    OPTIM
    -0.52
     read
    -0.52
    Scrollbar
    -0.51
    POSITIVE LOGITS
     writer
    2.44
     Writer
    2.23
    writer
    2.22
     writers
    2.20
     WRITER
    2.02
     Writers
    1.95
    Writer
    1.95
    Writers
    1.95
    writers
    1.92
     reporter
    1.82
    Activations Density 0.076%

    No Known Activations