© 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. 4074
    Prev
    Next
    INDEX
    Explanations

    mentions of magazines or magazine-related terminology

    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
     nakalista
    -0.73
     obicei
    -0.73
     uitz
    -0.63
     szolg
    -0.61
    amentals
    -0.61
    audiovisuel
    -0.57
     Drit
    -0.57
    setCustom
    -0.57
     mukana
    -0.56
     dreapta
    -0.56
    POSITIVE LOGITS
     magazine
    3.39
     Magazine
    3.16
     magazines
    2.91
     MAGAZINE
    2.89
    Magazine
    2.88
    magazine
    2.86
     Magazines
    2.59
    MAGAZINE
    2.48
    magaz
    2.23
     Magazin
    2.16
    Activations Density 0.026%

    No Known Activations