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. 11786
    Prev
    Next
    INDEX
    Explanations

    numbers and their relationships in the context of chemical structure

    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
    STALK
    -0.59
    apimachinery
    -0.52
    complexType
    -0.52
    quila
    -0.50
     Tula
    -0.50
    FARE
    -0.49
     vœux
    -0.48
    цездатний
    -0.47
     NDEBUG
    -0.47
    urgie
    -0.47
    POSITIVE LOGITS
    Билгалдахарш
    0.76
    awtextra
    0.69
    ]));
    
    0.61
    !*\
    0.60
    ())));
    0.59
    }}],
    0.58
     Himo
    0.57
     Muzeum
    0.55
    WindowConstants
    0.54
    "]));
    0.53
    Activations Density 0.036%

    No Known Activations