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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 113
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electrical and mechanical components of devices

    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
    Personendaten
    -0.73
     betweenstory
    -0.70
    rippa
    -0.67
    enumi
    -0.64
    ifoli
    -0.64
     yank
    -0.63
     ripping
    -0.62
     legit
    -0.61
     Byr
    -0.61
    CloseOperation
    -0.60
    POSITIVE LOGITS
    hereinafter
    0.52
     ThemeData
    0.51
     inconvénients
    0.50
     therefor
    0.49
     suitable
    0.49
    findpost
    0.48
     optionally
    0.48
     réception
    0.48
     adatto
    0.47
     Suitable
    0.46
    Activations Density 6.573%

    No Known Activations