© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14053
    Prev
    Next
    INDEX
    Explanations

    words indicating possession or belonging

    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
    Hozzáférés
    -0.79
    tagHelperRunner
    -0.77
     Chwiliwch
    -0.73
    PRNewswire
    -0.73
    bootstrapcdn
    -0.71
     NSCoder
    -0.69
     onOptions
    -0.68
    Geplaatst
    -0.67
    出版年
    -0.67
    ArrowToggle
    -0.65
    POSITIVE LOGITS
     eine
    0.56
    плуата
    0.52
     >=",
    0.49
     One
    0.47
    une
    0.47
     Eine
    0.46
     Another
    0.46
    Eine
    0.46
     another
    0.46
    unex
    0.46
    Activations Density 0.010%

    No Known Activations