© 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. 21405
    Prev
    Next
    INDEX
    Explanations

    numerical data and higher-level attributes in structured contexts

    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
     betweenstory
    -0.65
     itſelf
    -0.63
    Clik
    -0.62
     myſelf
    -0.62
    存于互联网档案馆
    -0.59
     themſelves
    -0.59
     ſeveral
    -0.56
     ſame
    -0.56
     inclu
    -0.55
     himſelf
    -0.54
    POSITIVE LOGITS
     <=",
    0.80
    NameInMap
    0.69
    setVerticalGroup
    0.61
     CWE
    0.60
     rémun
    0.57
    ">//
    0.57
    QMetaType
    0.55
    cyklopedia
    0.53
    Kilder
    0.52
    Jîn
    0.52
    Activations Density 0.000%

    No Known Activations