© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5765
    Prev
    Next
    INDEX
    Explanations

    mentions of being physically located inside a specific place or object

    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
     ویکی‌پدیای
    -0.87
     Ababa
    -0.71
     Mawr
    -0.69
     GIPHY
    -0.68
    posób
    -0.68
     toppers
    -0.68
    bootstrapcdn
    -0.67
    ритори
    -0.66
    ']],
    -0.65
    forcement
    -0.65
    POSITIVE LOGITS
     inside
    3.05
    Inside
    2.80
    inside
    2.75
     Inside
    2.73
     INSIDE
    2.52
    INSIDE
    2.25
     insides
    1.57
     outside
    1.46
     Outside
    1.41
    Outside
    1.39
    Activations Density 0.028%

    No Known Activations