© 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. 22-RES-MATRYOSHKA-DC
    7. 2737
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to problems, requests and reports

    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.22.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.22.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
    outSlope
    -0.48
     due
    -0.46
     devido
    -0.45
    Kapcsolódó
    -0.44
     zaradi
    -0.42
     suggesting
    -0.42
     نتيجة
    -0.41
    mentable
    -0.40
    UED
    -0.40
    гія
    -0.40
    POSITIVE LOGITS
     efficiently
    1.19
     correctly
    1.18
     properly
    1.11
     accurately
    1.07
    correctly
    1.06
    properly
    1.02
     adequately
    0.98
     cleanly
    0.98
     differently
    0.97
     Properly
    0.96
    Activations Density 1.585%

    No Known Activations