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. 11320
    Prev
    Next
    INDEX
    Explanations

    class definition and method declaration syntax in programming

    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
    /*
    -0.82
    ()?;
    -0.80
    Portale
    -0.79
    LookAnd
    -0.78
    ."));
    -0.78
    ;';
    -0.77
    клопе
    -0.75
     "}";
    -0.74
    APOLIS
    -0.74
     Италијани
    -0.73
    POSITIVE LOGITS
    __(
    1.13
    ագրություններ
    0.64
     diri
    0.50
    tagHelper
    0.49
     للمعارف
    0.49
    蹄
    0.49
    ().__
    0.48
     riport
    0.45
    this
    0.44
     فريبيس
    0.44
    Activations Density 0.004%

    No Known Activations