Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15178
    Prev
    Next
    INDEX
    Explanations

    references to significant or emphasized aspects related to the real, true, or human nature of something

    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
    ēc
    -0.52
     a
    -0.51
     realice
    -0.51
     tulee
    -0.50
    稲田
    -0.45
    슷
    -0.44
     tengas
    -0.43
     adecuadas
    -0.43
     adequad
    -0.43
     dotato
    -0.43
    POSITIVE LOGITS
     nahilalakip
    0.96
     Monfieur
    0.91
     يتيمه
    0.90
     Efq
    0.76
     whoſe
    0.74
    OrNil
    0.74
    protoimpl
    0.72
    fjspx
    0.72
    AccessorTable
    0.72
    thâu
    0.71
    Activations Density 0.546%

    No Known Activations