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. 9476
    Prev
    Next
    INDEX
    Explanations

    repetitive conjunctions in lists or phrases

    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
     doInBackground
    -0.63
    StoreMessageInfo
    -0.55
    CodeAttribute
    -0.54
     Tapatalk
    -0.50
     Deceased
    -0.50
     Jol
    -0.49
    AGAT
    -0.48
     bro
    -0.48
     niemi
    -0.47
     haber
    -0.47
    POSITIVE LOGITS
    enumi
    0.89
    يكب
    0.66
    /**
    0.62
     incomplète
    0.61
    PerformLayout
    0.60
    IsMutable
    0.60
     contextLoads
    0.59
    MigrationBuilder
    0.59
    ValueStyle
    0.58
    FieldNumber
    0.57
    Activations Density 0.009%

    No Known Activations