© 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. 983
    Prev
    Next
    INDEX
    Explanations

    scientific text containing physical measurements and thresholds

    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
    tdessen
    -0.54
    ]--;
    -0.50
     AssemblyTitle
    -0.49
     المعيارى
    -0.48
    srcs
    -0.47
    Bronnen
    -0.47
    ContentAsync
    -0.46
    исленность
    -0.44
     Rus
    -0.44
    ล้ว
    -0.43
    POSITIVE LOGITS
     threshold
    1.37
     thresholds
    1.20
     seuil
    1.14
    threshold
    1.10
     Threshold
    1.06
    Threshold
    1.00
     batas
    0.93
    thresholds
    0.92
    THRESHOLD
    0.92
     thresh
    0.92
    Activations Density 2.638%

    No Known Activations