Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 25675
    Prev
    Next
    INDEX
    Explanations

    instances of the preposition "in."

    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
    Autoritní
    -1.05
     незавершена
    -1.02
     myſelf
    -1.02
    PreferredItem
    -0.99
    XmlAccessorType
    -0.96
     Theſe
    -0.92
    ViewFeatures
    -0.90
     ſeveral
    -0.89
     Efq
    -0.89
     ſta
    -0.88
    POSITIVE LOGITS
    ,
    0.62
     of
    0.61
     or
    0.52
    .
    0.52
     simple
    0.50
     
    0.48
     (
    0.48
     total
    0.48
    <eos>
    0.48
     also
    0.46
    Activations Density 0.018%

    No Known Activations