© 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. 43
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to functions and equations

    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
    
    -0.56
    RefNanny
    -0.53
    ItemBackground
    -0.51
     setTotal
    -0.50
    </blockquote>
    -0.50
     Ause
    -0.47
     endif
    -0.47
     basta
    -0.46
    gnore
    -0.46
    APIView
    -0.46
    POSITIVE LOGITS
    |}{$
    0.94
    theless
    0.83
     مُعرِّف
    0.79
    ={`${
    0.77
     NACIONAL
    0.73
    ednesdays
    0.73
     &___
    0.70
    質な
    0.70
     насељу
    0.69
     tournage
    0.69
    Activations Density 4.409%

    No Known Activations