© 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. 129
    Prev
    Next
    INDEX
    Explanations

    conditional phrases expressing hypothetical scenarios or actions

    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
     onAnimation
    -0.77
     Maguire
    -0.73
     JpaRepository
    -0.71
    nsic
    -0.69
    dataSet
    -0.66
     Lipa
    -0.65
    FromArgb
    -0.64
    ij
    -0.63
    Laure
    -0.63
    dataList
    -0.63
    POSITIVE LOGITS
     WOULD
    1.79
     would
    1.77
     Would
    1.76
    Would
    1.75
    would
    1.74
     gdyby
    1.19
     wäre
    1.14
     Wouldn
    1.13
    wouldn
    1.13
     würde
    1.12
    Activations Density 1.514%

    No Known Activations