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. 15001
    Prev
    Next
    INDEX
    Explanations

    the structure and elements of programming code specifically related to player statistics in a game context

    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
     bir
    -0.47
     get
    -0.41
    x
    -0.41
    n
    -0.41
     conto
    -0.41
     dat
    -0.40
     E
    -0.39
     do
    -0.39
    X
    -0.39
    元
    -0.39
    POSITIVE LOGITS
    SourceChecksum
    1.19
    NgModule
    1.16
     invokingState
    1.08
     itſelf
    1.08
     NgModule
    1.07
    basicConfig
    1.06
    GenerationType
    1.04
    ValueStyle
    1.03
     $_"
    1.01
    ſelves
    0.99
    Activations Density 0.275%

    No Known Activations