© 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. 1516
    Prev
    Next
    INDEX
    Explanations

    contexts where something is easy to do

    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
    Negative Logits
    GEBURTSDATUM
    -0.77
     ProtoMessage
    -0.77
     تانيه
    -0.72
     AssemblyTitle
    -0.70
    chromedriver
    -0.68
    randomUUID
    -0.65
    enumii
    -0.63
     ModelExpression
    -0.63
     réguli
    -0.62
     */
    -0.62
    POSITIVE LOGITS
     easy
    1.34
     Easy
    1.33
    Easy
    1.30
    EASY
    1.27
    easy
    1.27
     EASY
    1.23
     kolay
    1.05
    Easier
    1.04
     Easier
    1.03
     easier
    1.02
    Activations Density 0.659%

    No Known Activations