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. 18544
    Prev
    Next
    INDEX
    Explanations

    instances of the word "even."

    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
     it
    -0.75
     Z
    -0.66
     we
    -0.60
     
    -0.59
     T
    -0.59
     there
    -0.57
    <eos>
    -0.56
     It
    -0.54
     M
    -0.52
     he
    -0.52
    POSITIVE LOGITS
     myſelf
    1.12
     itſelf
    1.09
    ſelf
    1.06
     Anſ
    1.06
     photolibrary
    1.05
     houſe
    1.01
    ſelves
    0.99
     Efq
    0.97
     Jefus
    0.97
     ་་
    0.96
    Activations Density 0.012%

    No Known Activations