© 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. 24-RES-MATRYOSHKA-DC
    7. 1468
    Prev
    Next
    INDEX
    Explanations

    words and short phrases in natural language that describe social interactions

    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.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     its
    -0.55
     rumahnya
    -0.54
    ")->
    -0.54
    its
    -0.54
    alanya
    -0.54
    ęku
    -0.53
    CloseOperation
    -0.53
     Its
    -0.52
    Its
    -0.52
    менте
    -0.51
    POSITIVE LOGITS
     my
    4.03
    my
    3.05
     mijn
    2.81
    我的
    2.53
     meu
    2.48
     meiner
    2.47
     minha
    2.44
     meus
    2.41
     meinem
    2.39
     meine
    2.38
    Activations Density 1.971%

    No Known Activations