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. 8859
    Prev
    Next
    INDEX
    Explanations

    the presence of mathematical notation and structural elements commonly found in equations

    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
     وتسجيلات
    -0.86
     nahilalakip
    -0.84
    \{\\
    -0.80
     referenties
    -0.77
    Спасылкі
    -0.76
    Portail
    -0.76
    NUMX
    -0.75
    Filmografie
    -0.70
     createStore
    -0.70
    例句
    -0.69
    POSITIVE LOGITS
    lles
    0.49
    UST
    0.47
    しょ
    0.47
    rolid
    0.47
     neige
    0.46
     transfieras
    0.45
    ArgsConstructor
    0.44
    mtx
    0.44
     gj
    0.44
    et
    0.43
    Activations Density 0.020%

    No Known Activations