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. 23129
    Prev
    Next
    INDEX
    Explanations

    references to real numbers and their properties

    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
    CodeAttribute
    -0.75
    Tikang
    -0.69
    aarrggbb
    -0.68
     дописавши
    -0.64
    Искәрмәләр
    -0.61
    pahan
    -0.58
    webElementXpaths
    -0.57
    ierend
    -0.57
    fid
    -0.57
    ArgsConstructor
    -0.56
    POSITIVE LOGITS
     Triassic
    0.55
     desay
    0.55
    yesi
    0.52
     Baptists
    0.50
     Descartes
    0.50
    audiovisuel
    0.49
     barbarians
    0.49
    Rien
    0.47
     viande
    0.47
    IZONTAL
    0.47
    Activations Density 0.005%

    No Known Activations