© 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. 11083
    Prev
    Next
    INDEX
    Explanations

    references to ownership or possession

    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
    رشف
    -0.78
    Искәрмәләр
    -0.72
     contextLoads
    -0.69
    rungsseite
    -0.66
    }});
    -0.66
     ویکی‌پدیا
    -0.65
    Normdaten
    -0.63
     '\\;'
    -0.62
     Normdatei
    -0.61
     Drapeau
    -0.61
    POSITIVE LOGITS
    nestjs
    0.59
    ibatis
    0.59
    ForValue
    0.53
     ideas
    0.51
     Vase
    0.51
    案
    0.50
    nasse
    0.48
    ℉
    0.47
    onda
    0.47
    tanooga
    0.46
    Activations Density 0.010%

    No Known Activations