© 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. 12-RES-MATRYOSHKA-DC
    7. 20858
    Prev
    Next
    INDEX
    Explanations

    questions or queries within the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    awaiter
    -0.74
    bootstrapcdn
    -0.50
     cur
    -0.49
    ibatis
    -0.48
     o
    -0.47
     -
    -0.47
    uta
    -0.47
    ote
    -0.46
    elemField
    -0.46
    ké
    -0.45
    POSITIVE LOGITS
     للمعارف
    0.94
    expandindo
    0.86
     تانيه
    0.84
     tartalomajánló
    0.79
    NUMX
    0.75
     ་་
    0.73
    !")
    0.72
     Xunit
    0.71
    .")]
    0.71
    ."</
    0.71
    Activations Density 0.022%

    No Known Activations