© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14538
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific analysis and experiments

    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
    Rhestr
    -0.56
    PostConstruct
    -0.53
     unknownFields
    -0.50
    Hechos
    -0.47
    hline
    -0.45
    Véxase
    -0.45
    omitempty
    -0.45
     pleaſure
    -0.45
     houſe
    -0.44
    XmlEnum
    -0.44
    POSITIVE LOGITS
    TypedDataSet
    0.84
    دانشنامهٔ
    0.81
    脚注の使い方
    0.74
    ValueStyle
    0.71
    richTextPanel
    0.69
     kaarangay
    0.63
     дописавши
    0.59
     חיצוניים
    0.57
    matchCondition
    0.57
     hObject
    0.56
    Activations Density 0.220%

    No Known Activations