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. 29700
    Prev
    Next
    INDEX
    Explanations

    elements and references from the Star Wars universe

    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
    دانشنامهٔ
    -0.91
    quehanna
    -0.68
     BoxFit
    -0.66
    esgue
    -0.65
    Zacks
    -0.63
    ]";
    -0.62
    openConnection
    -0.61
    rabh
    -0.59
    ποτε
    -0.59
    NetworkInfo
    -0.58
    POSITIVE LOGITS
     Jedi
    0.96
     Darth
    0.93
     Skywalker
    0.90
     Yoda
    0.89
     Vader
    0.88
     Leia
    0.87
    Jedi
    0.84
     lightsaber
    0.82
    Darth
    0.81
     jedi
    0.81
    Activations Density 0.023%

    No Known Activations