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. 29
    Prev
    Next
    INDEX
    Explanations

    comparative statements indicating differences between groups or conditions

    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
    vov
    -0.51
     RSV
    -0.48
     JSP
    -0.46
     Verbindung
    -0.46
    X
    -0.46
     Romans
    -0.45
    scss
    -0.45
    sb
    -0.43
    ary
    -0.43
    irinha
    -0.42
    POSITIVE LOGITS
     THAN
    1.07
     than
    1.06
    MigrationBuilder
    0.98
     those
    0.97
     decât
    0.97
     saites
    0.96
     оригіналу
    0.95
    StoreMessageInfo
    0.93
    Than
    0.91
    InjectAttribute
    0.88
    Activations Density 3.135%

    No Known Activations