© 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. 15373
    Prev
    Next
    INDEX
    Explanations

    references to logical proof steps or mathematical demonstrations

    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
     I
    -0.59
     If
    -0.56
    ständ
    -0.55
      
    -0.54
       
    -0.47
     do
    -0.45
     
    -0.44
     am
    -0.43
    ########.
    -0.43
     are
    -0.43
    POSITIVE LOGITS
     Efq
    1.07
     photolibrary
    0.96
     betweenstory
    0.93
     myſelf
    0.93
     AppColors
    0.92
     doubtnut
    0.88
    MessageOf
    0.86
     crdi
    0.85
     himſelf
    0.85
     vectorstock
    0.84
    Activations Density 0.047%

    No Known Activations