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. 20333
    Prev
    Next
    INDEX
    Explanations

    negations or instances where something is absent or not present

    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
     createState
    -0.59
    Resumen
    -0.55
    kopf
    -0.54
     oreille
    -0.51
     toate
    -0.50
     Loth
    -0.50
     hầu
    -0.49
     least
    -0.49
    coast
    -0.47
     EOF
    -0.47
    POSITIVE LOGITS
    httphttps
    0.80
    WireFormatLite
    0.76
    Geplaatst
    0.65
     يتيمه
    0.62
     referenties
    0.61
    InjectAttribute
    0.61
    apimachinery
    0.60
    要不要
    0.59
     pinulongan
    0.58
    alagi
    0.57
    Activations Density 0.010%

    No Known Activations