© 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. 19177
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms related to probabilistic models

    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
     ainfi
    -0.85
     Theſe
    -0.82
     itſelf
    -0.78
    GEBURTSDATUM
    -0.77
     auroit
    -0.77
     Monfieur
    -0.75
    endphp
    -0.75
     Italijani
    -0.73
    IsMutable
    -0.73
     سكانية
    -0.73
    POSITIVE LOGITS
    ↵↵
    0.38
    ble
    0.37
    laug
    0.36
    parseFrom
    0.35
    ={'
    0.34
    Pa
    0.34
    дев
    0.34
     (
    0.34
     my
    0.33
    my
    0.33
    Activations Density 0.094%

    No Known Activations