© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4096
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and places

    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
     sessile
    -0.57
    ArgsConstructor
    -0.53
    Slf
    -0.50
     PhpStorm
    -0.50
    semantics
    -0.50
    abetes
    -0.49
    esModule
    -0.49
    opardy
    -0.49
    ̣i
    -0.47
     كومونز
    -0.45
    POSITIVE LOGITS
    matchCondition
    0.93
     Biôgrafia
    0.86
     Paglinawan
    0.85
     defaultstate
    0.81
     tartalomajánló
    0.80
    دانشنامهٔ
    0.80
    StoryboardSegue
    0.77
    Personendaten
    0.76
    adpleegd
    0.73
     cherchés
    0.70
    Activations Density 1.460%

    No Known Activations