© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13391
    Prev
    Next
    INDEX
    Explanations

    references to specific, often scientific or technical, terms related to the identification, classification, and history of biological species or groups

    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
     Falling
    -0.63
    Falling
    -0.54
    RequiresApi
    -0.53
    teva
    -0.53
    enumi
    -0.52
    Vorlage
    -0.52
    ">/
    -0.52
    hous
    -0.51
    %)$
    -0.49
    GenerationType
    -0.48
    POSITIVE LOGITS
    ussis
    1.02
     Dane
    0.83
     vuitton
    0.79
    tlement
    0.77
    apimachinery
    0.74
    }^{+\
    0.73
    expandindo
    0.73
     lows
    0.72
    Samoa
    0.71
     highs
    0.71
    Activations Density 0.073%

    No Known Activations