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. 11714
    Prev
    Next
    INDEX
    Explanations

    code comments or annotations, particularly those starting with specific symbols

    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
     Infórmanos
    -0.76
    Ma
    -0.74
     Bona
    -0.73
    istani
    -0.71
    nas
    -0.71
    ona
    -0.69
     Ma
    -0.67
     Oakes
    -0.66
    க்க
    -0.65
    al
    -0.65
    POSITIVE LOGITS
    ///
    1.47
     ///
    1.20
    ///
    
    0.88
    ///<
    0.83
    /////
    0.81
     }?>
    0.79
    }}/>
    0.79
    ');?>
    0.77
    phazard
    0.76
    ագրություններ
    0.74
    Activations Density 0.006%

    No Known Activations