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. 24731
    Prev
    Next
    INDEX
    Explanations

    patterns related to routing and controller actions in web applications

    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
     MaterialApp
    -0.63
    IntoConstraints
    -0.54
     Plummer
    -0.52
    maining
    -0.51
     liv
    -0.50
    ])).
    -0.49
    $-\
    -0.49
    وند
    -0.49
    shad
    -0.49
    ELS
    -0.48
    POSITIVE LOGITS
    #+#
    0.75
     Exacts
    0.71
    TargetException
    0.69
     Вікі
    0.67
     >=",
    0.66
    AndEndTag
    0.59
     חיצוניים
    0.58
    তথ্যসূত্র
    0.57
    AddTagHelper
    0.57
    tagext
    0.56
    Activations Density 0.020%

    No Known Activations