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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19401
    Prev
    Next
    INDEX
    Explanations

    visual content elements or file types

    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
    曖昧さ回避
    -0.83
    SBATCH
    -0.78
     disponibilités
    -0.75
    KommentareTeilen
    -0.74
    newswire
    -0.74
    simpleType
    -0.72
    ſelves
    -0.72
    Extinguishing
    -0.70
     myſelf
    -0.69
     protoimpl
    -0.68
    POSITIVE LOGITS
    酪
    0.50
    esgue
    0.50
    琦
    0.45
     Attach
    0.45
    '>{
    0.45
    horst
    0.43
     Arbeiten
    0.41
    ibli
    0.41
    GARET
    0.41
    اعمال
    0.40
    Activations Density 0.014%

    No Known Activations