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. 6365
    Prev
    Next
    INDEX
    Explanations

    path and directory structures in file system 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
    enzie
    -0.54
    bid
    -0.54
    Barrett
    -0.53
     afin
    -0.51
    cdf
    -0.51
     shootings
    -0.50
     Diaries
    -0.50
     Barrett
    -0.50
    twe
    -0.50
     diaries
    -0.49
    POSITIVE LOGITS
     usr
    1.13
    usr
    1.04
     itſelf
    0.90
    +#+#
    0.81
     themſelves
    0.77
     Theſe
    0.76
     referenties
    0.75
    Usr
    0.75
    ніципалі
    0.74
    BibitemShut
    0.74
    Activations Density 0.028%

    No Known Activations