© 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. 12-RES-MATRYOSHKA-DC
    7. 5735
    Prev
    Next
    INDEX
    Explanations

    the frequency of the pronoun "we" and its variations in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -1.01
     HttpNotFound
    -0.99
    تقاوى
    -0.98
     contextLoads
    -0.95
    uxxxx
    -0.95
     Efq
    -0.95
     beginnetje
    -0.94
     ComVisible
    -0.93
    Viitteet
    -0.93
    Datuak
    -0.92
    POSITIVE LOGITS
     a
    0.52
    後日
    0.49
      
    0.48
     –
    0.48
    #
    0.47
     di
    0.47
    ?
    0.47
     
    0.46
    ↵↵
    0.46
     Note
    0.46
    Activations Density 0.186%

    No Known Activations