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. 15953
    Prev
    Next
    INDEX
    Explanations

    the formatting and structure of mathematical expressions and certain statistical terms

    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
     
    -0.53
    lipid
    -0.48
     left
    -0.41
     ater
    -0.40
    ity
    -0.40
     pojed
    -0.38
    lipids
    -0.37
    탈
    -0.37
     wire
    -0.37
     still
    -0.36
    POSITIVE LOGITS
    AndEndTag
    0.99
    Попис
    0.83
    Carriera
    0.81
    endphp
    0.81
    ValueStyle
    0.79
     مشين
    0.78
    TargetException
    0.77
    InstrumentedTest
    0.77
    Personendaten
    0.77
    ViewImports
    0.76
    Activations Density 0.015%

    No Known Activations