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. 6160
    Prev
    Next
    INDEX
    Explanations

    references to authorship and contributions in research papers

    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
    didSet
    -0.64
    reloadData
    -0.48
    /*:
    -0.46
    ades
    -0.45
     too
    -0.43
     Goldstein
    -0.43
     mus
    -0.42
     tray
    -0.42
    arques
    -0.42
     her
    -0.42
    POSITIVE LOGITS
     للاسماء
    1.05
    thâu
    0.85
     Roskov
    0.85
    Portály
    0.82
    kloped
    0.79
    TagMode
    0.74
     الحره
    0.73
    Pautan
    0.71
     Theſe
    0.71
    SourceChecksum
    0.71
    Activations Density 0.005%

    No Known Activations