© 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. 10817
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to hidden or secretive topics

    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
    ſelves
    -0.85
     Majefty
    -0.85
    ſelf
    -0.84
     AssemblyTitle
    -0.75
     Efq
    -0.75
    ✨:
    -0.74
    InstanceState
    -0.73
     Theſe
    -0.73
    RetentionPolicy
    -0.73
     pleaſure
    -0.72
    POSITIVE LOGITS
    tır
    0.46
     ویکی‌پدی
    0.44
     da
    0.39
    da
    0.39
     data
    0.38
    ,
    0.38
    pd
    0.38
     const
    0.38
    .
    0.37
     direct
    0.36
    Activations Density 0.019%

    No Known Activations