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. 24977
    Prev
    Next
    INDEX
    Explanations

    instances of function and method calls in programming syntax

    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
    <bos>
    -0.51
    趾
    -0.46
    roach
    -0.45
     gerekir
    -0.44
    moduleId
    -0.44
    Morfologia
    -0.43
    走向
    -0.43
     gidi
    -0.43
    مود
    -0.42
    vle
    -0.42
    POSITIVE LOGITS
    ConstraintMaker
    0.83
     NSCoder
    0.80
    EDEFAULT
    0.72
     فريبيس
    0.70
    verwijspagina
    0.69
    Rhestr
    0.68
    AccessorTable
    0.68
    IntoConstraints
    0.67
     يتيمه
    0.66
    脚注の使い方
    0.66
    Activations Density 0.025%

    No Known Activations