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. 22752
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols indicating operations

    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
    الحياه
    -0.75
    openzeppelin
    -0.60
    ArgsConstructor
    -0.58
     cerámica
    -0.58
    DispatchQueue
    -0.55
     logiciels
    -0.55
    مراجع
    -0.52
    esac
    -0.50
    ModelBuilder
    -0.47
     privilégi
    -0.47
    POSITIVE LOGITS
    InitVars
    0.64
     HttpNotFound
    0.56
    ImageContext
    0.56
    InstrumentedTest
    0.56
    FXMLLoader
    0.55
    hattan
    0.54
    KommentareTeilen
    0.54
    发表于
    0.52
    >%
    0.51
     {},
    
    0.50
    Activations Density 0.001%

    No Known Activations