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. 8705
    Prev
    Next
    INDEX
    Explanations

    quoted content or string literals in code or markup

    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
    الإنجليزية
    -0.63
     Référence
    -0.59
     Baillargeon
    -0.54
    werf
    -0.50
    RemoveField
    -0.50
     Abdul
    -0.48
    PerformLayout
    -0.47
     Mixed
    -0.46
     resourceCulture
    -0.46
    Abdul
    -0.46
    POSITIVE LOGITS
    Datuak
    0.77
    CopyWith
    0.74
    }]);
    0.69
    出版年
    0.68
    RegressionTest
    0.67
    ()]);
    0.67
    WindowConstants
    0.66
    省市镇
    0.65
    EndContext
    0.65
    )});
    0.64
    Activations Density 0.009%

    No Known Activations