© 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. 18-RES-MATRYOSHKA-DC
    7. 1317
    Prev
    Next
    INDEX
    Explanations

    phrases that are common in scientific study designs and results

    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.18.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.18.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
    ---*/
    -0.54
    MessageTagHelper
    -0.53
    endfor
    -0.52
    Tired
    -0.52
    FieldDescriptor
    -0.52
    much
    -0.52
     progressivement
    -0.51
    ']").
    -0.50
    []){
    -0.50
    Much
    -0.50
    POSITIVE LOGITS
     either
    1.35
     almeno
    1.27
    Either
    1.24
    either
    1.24
     Either
    1.20
     atleast
    1.19
    至少
    1.17
     mindestens
    1.16
     ≥
    1.15
     setidaknya
    1.10
    Activations Density 3.158%

    No Known Activations