© 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. 22-RES-MATRYOSHKA-DC
    7. 2929
    Prev
    Next
    INDEX
    Explanations

    nouns, numbers and prepositions, particularly those used when giving instructions or directions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     wipers
    -0.66
    DockStyle
    -0.65
     مرئيه
    -0.64
     ladders
    -0.63
     bridges
    -0.62
    存于互联网档案馆
    -0.61
    PhysRevLett
    -0.59
    bridges
    -0.59
    Geplaatst
    -0.58
     oars
    -0.58
    POSITIVE LOGITS
     box
    0.95
     container
    0.88
    container
    0.82
    box
    0.81
     Box
    0.79
     boxes
    0.79
     containers
    0.78
    Box
    0.75
     BOX
    0.74
    Container
    0.73
    Activations Density 0.397%

    No Known Activations