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. 22648
    Prev
    Next
    INDEX
    Explanations

    a form of template programming or structure definitions in programming code

    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
     Wachs
    -0.62
    RegressionTest
    -0.56
     TAGS
    -0.56
    ropractic
    -0.55
     Haft
    -0.54
    SneakyThrows
    -0.54
    hihi
    -0.53
    anthus
    -0.52
    nyard
    -0.52
    okka
    -0.52
    POSITIVE LOGITS
    NameInMap
    1.09
    ⓧ
    1.02
    
    0.94
     ModelExpression
    0.90
     виправивши
    0.85
     مشين
    0.81
    GraphicsUnit
    0.81
    évaluateur
    0.78
     oprot
    0.78
     protoimpl
    0.75
    Activations Density 0.002%

    No Known Activations