© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 53
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to functions and calculus

    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
    ))^{
    -0.97
    ))^
    -0.82
    })^{
    -0.75
    ))*
    -0.75
    )}^{
    -0.73
    ])*
    -0.73
    ())),
    -0.73
     
    -0.71
    ])),
    -0.70
    <eos>
    -0.70
    POSITIVE LOGITS
     AssemblyCulture
    1.02
    enumi
    0.98
     ComVisible
    0.96
    IntoConstraints
    0.96
    onViewCreated
    0.94
     myſelf
    0.94
    ViewFeatures
    0.93
    ConstraintMaker
    0.91
    djangoproject
    0.89
    +#+#
    0.87
    Activations Density 8.569%

    No Known Activations