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. 26795
    Prev
    Next
    INDEX
    Explanations

    references to legal statutes and judicial decisions

    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
     pioggia
    -0.63
    AndEndTag
    -0.62
    المناصب
    -0.55
     poffe
    -0.54
    irvana
    -0.53
     pleaſure
    -0.49
     battaglia
    -0.49
     fhew
    -0.47
     tarko
    -0.47
    Ex
    -0.47
    POSITIVE LOGITS
    ])));
    0.77
    ValueStyle
    0.72
    TagHelper
    0.69
    存于互联网档案馆
    0.69
    ">';
    0.68
    )"),
    0.67
    }`;
    0.67
     Référence
    0.66
    SequentialGroup
    0.65
    )*/
    0.65
    Activations Density 0.003%

    No Known Activations