© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 388
    Prev
    Next
    INDEX
    Explanations

    words that start with 'stat' and a few political terms

    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
    ])):
    -0.70
    __':
    -0.61
    timewa
    -0.58
    ollectionView
    -0.57
     kasarigan
    -0.57
    tanleria
    -0.56
     swell
    -0.56
    Amen
    -0.55
     dager
    -0.54
     dirty
    -0.53
    POSITIVE LOGITS
     quo
    0.85
     AssemblyCulture
    0.79
    MigrationBuilder
    0.71
     Stur
    0.71
    STE
    0.68
     Stal
    0.68
     Ста
    0.65
    Sta
    0.63
    stb
    0.62
     Sta
    0.62
    Activations Density 1.925%

    No Known Activations