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. 9303
    Prev
    Next
    INDEX
    Explanations

    references to file handling and system structures 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
    ValueStyle
    -0.80
     typelib
    -0.69
    Personensuche
    -0.66
    دانشنامهٔ
    -0.63
     beginnetje
    -0.62
    QMetaType
    -0.62
     stazione
    -0.61
    providedIn
    -0.60
    ReusableCell
    -0.60
    EndGlobalSection
    -0.60
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.56
    Autoritní
    0.56
    offsetWidth
    0.47
     stili
    0.47
    legi
    0.46
     esternos
    0.46
    heça
    0.46
    propTypes
    0.45
    addLine
    0.44
    
    0.44
    Activations Density 0.001%

    No Known Activations