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. 15133
    Prev
    Next
    INDEX
    Explanations

    specific locations and entities, particularly named places and geographical references

    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
    WebVitals
    -0.81
     '{@
    -0.76
    antMatchers
    -0.76
     CreateTagHelper
    -0.75
    енча
    -0.75
     GenerationType
    -0.74
     nahilalakip
    -0.74
     indisponible
    -0.71
     للاسماء
    -0.71
    byter
    -0.71
    POSITIVE LOGITS
     zaś
    0.57
     giapp
    0.56
     imidlertid
    0.56
    ToEdit
    0.56
     jedenfalls
    0.54
     vierge
    0.54
     internationales
    0.53
     newName
    0.53
     turísticos
    0.53
    óság
    0.52
    Activations Density 0.121%

    No Known Activations