© 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. 16745
    Prev
    Next
    INDEX
    Explanations

    instances of the word "solve" followed by a number

    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
     Anſ
    -0.71
     Tér
    -0.69
     myſelf
    -0.66
     ſtate
    -0.66
     Efq
    -0.66
     juſ
    -0.65
     poffe
    -0.65
     Gabb
    -0.65
     كومونز
    -0.64
     themſelves
    -0.64
    POSITIVE LOGITS
    تقاوى
    0.65
     JpaRepository
    0.62
    complexContent
    0.58
     propOrder
    0.58
    GEBURTSDATUM
    0.57
     pinulongan
    0.56
     initComponents
    0.56
    webElementXpaths
    0.53
    AddField
    0.52
    testify
    0.50
    Activations Density 0.003%

    No Known Activations