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. 233
    Prev
    Next
    INDEX
    Explanations

    nested parentheses and structures in mathematical expressions

    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
    }]);
    -0.68
     Stu
    -0.66
    сто
    -0.61
     nulle
    -0.59
    ")))
    -0.59
    ]));
    -0.58
    ]-->
    -0.58
    jface
    -0.57
     kema
    -0.56
    ']))
    -0.56
    POSITIVE LOGITS
    ">(</
    1.57
    >(</
    1.41
    (\
    1.35
     }^{(
    1.32
    ($(
    1.27
    ("(
    1.27
    __(
    1.27
    (
    1.24
    }(
    1.23
     ($(
    1.20
    Activations Density 1.636%

    No Known Activations