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. 26811
    Prev
    Next
    INDEX
    Explanations

    key performance indicators related to organizations and their structures

    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
    EndGlobalSection
    -0.81
    Datuak
    -0.79
    +#+#
    -0.78
     <<<<<<<<<<<<<<
    -0.75
     useAppContext
    -0.74
    LookAnd
    -0.72
    SharedDtor
    -0.70
     Савезне
    -0.69
     numberOfRows
    -0.68
     initComponents
    -0.67
    POSITIVE LOGITS
     nahilalakip
    0.47
    nossa
    0.42
    vermectin
    0.42
    族館
    0.42
    rapeau
    0.42
    θεια
    0.42
     canard
    0.41
    vikle
    0.41
    ecraft
    0.40
    間に
    0.40
    Activations Density 0.003%

    No Known Activations