© 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. 1485
    Prev
    Next
    INDEX
    Explanations

    statistical information, especially percentages and numbers within parentheses, often related to survey results or data analysis.

    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
    enumi
    -0.70
     cref
    -0.63
    SequentialGroup
    -0.54
    leyebilirsiniz
    -0.51
    jsonwebtoken
    -0.51
     it
    -0.49
    FileDescriptor
    -0.48
    cteur
    -0.46
    ècie
    -0.46
    vindo
    -0.46
    POSITIVE LOGITS
     Nearly
    1.28
     nearly
    1.28
     eighty
    1.27
     Seventy
    1.23
    Nearly
    1.22
     seventy
    1.22
     Eighty
    1.22
    nearly
    1.21
     majority
    1.20
     ninety
    1.18
    Activations Density 2.078%

    No Known Activations