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. 31904
    Prev
    Next
    INDEX
    Explanations

    notations and references to mathematical proofs and arguments

    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
    tvguidetime
    -0.91
     consultato
    -0.78
    
    -0.78
     MainAxisSize
    -0.77
     myſelf
    -0.77
    PerformLayout
    -0.76
     resourceCulture
    -0.76
     createContext
    -0.75
     betweenstory
    -0.75
     NSCoder
    -0.74
    POSITIVE LOGITS
     Please
    0.55
     please
    0.52
     bitte
    0.50
     Check
    0.49
     po
    0.48
     check
    0.47
    check
    0.45
     w
    0.45
    ropo
    0.45
    Please
    0.44
    Activations Density 0.094%

    No Known Activations