© 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. 19300
    Prev
    Next
    INDEX
    Explanations

    the word "as."

    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
     CreateTagHelper
    -0.93
    ValueStyle
    -0.85
     كومونز
    -0.80
    ../
    -0.79
    tahankan
    -0.77
    Demikian
    -0.73
    AnchorStyles
    -0.71
     отношению
    -0.69
    Siamo
    -0.68
     unangemessene
    -0.67
    POSITIVE LOGITS
     Zacks
    0.65
     Justine
    0.62
    ly
    0.57
    duma
    0.56
     Nunn
    0.56
    pragma
    0.56
    zeera
    0.56
     Vicksburg
    0.55
    <h2>
    0.54
    lyn
    0.54
    Activations Density 0.007%

    No Known Activations