© 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. 5722
    Prev
    Next
    INDEX
    Explanations

    formal mathematical notation and definitions

    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
    ंदीखरीदारी
    -1.01
     itſelf
    -1.00
     <=",
    -0.89
    extAlignment
    -0.88
     tartalomajánló
    -0.83
    featureID
    -0.79
    ngdoc
    -0.79
    Vidite
    -0.76
    BIÉN
    -0.76
     ddelweddau
    -0.76
    POSITIVE LOGITS
    ↵↵
    0.65
     a
    0.56
     C
    0.54
    ↵
    0.53
     .
    0.52
    ager
    0.52
    .
    0.52
    <eos>
    0.52
    ars
    0.52
     
    0.52
    Activations Density 0.147%

    No Known Activations