© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13875
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "incarceration" or being sentenced or imprisoned

    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
    encing
    -1.49
    ences
    -1.35
    enced
    -1.27
    encer
    -0.83
    ENCES
    -0.82
    存于互联网档案馆
    -0.74
    ENCED
    -0.74
    ENC
    -0.66
     fences
    -0.66
     للمعارف
    -0.64
    POSITIVE LOGITS
    ence
    1.82
    yntaxException
    0.60
    átky
    0.57
     NSCoder
    0.54
    ποι
    0.54
    Хьажоргаш
    0.54
    ########.
    0.54
     PyTuple
    0.54
    AlterField
    0.53
    يكب
    0.53
    Activations Density 0.001%

    No Known Activations