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. 196
    Prev
    Next
    INDEX
    Explanations

    the word "with" and its variations in different contexts

    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
    AnchorStyles
    -0.89
    Hentet
    -0.87
     onOptions
    -0.85
     leaſt
    -0.81
     themſelves
    -0.80
    InputBorder
    -0.80
     发表于
    -0.79
    testens
    -0.79
    adır
    -0.78
     Sae
    -0.77
    POSITIVE LOGITS
     With
    1.59
    with
    1.57
     with
    1.55
     WITH
    1.53
    With
    1.43
    WITH
    1.32
     avec
    1.27
     Avec
    1.20
    Avec
    1.13
     Witherspoon
    1.00
    Activations Density 1.853%

    No Known Activations