© 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. 23197
    Prev
    Next
    INDEX
    Explanations

    references to sketches or drawings

    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
    Negative Logits
    CultureInfo
    -0.84
    IsPostBack
    -0.79
     IUPAC
    -0.79
    Vezi
    -0.73
    NegativeButton
    -0.72
    WriteAttribute
    -0.70
     AppBar
    -0.67
     IFA
    -0.66
     Wals
    -0.66
     anún
    -0.66
    POSITIVE LOGITS
     Sketch
    1.59
     sketch
    1.55
     SKETCH
    1.48
    Sketch
    1.48
    sketch
    1.45
     sketches
    1.43
     sketching
    1.43
     Sketches
    1.21
     sketched
    1.20
     sketchbook
    0.89
    Activations Density 0.001%

    No Known Activations