© 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. 18436
    Prev
    Next
    INDEX
    Explanations

    references to structured or mathematical notations in scientific 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
     itſelf
    -0.92
     himſelf
    -0.88
     للمعارف
    -0.88
     Theſe
    -0.88
     myſelf
    -0.85
     themſelves
    -0.84
     auffi
    -0.82
     Monfieur
    -0.82
     resourceCulture
    -0.81
     pleaſure
    -0.81
    POSITIVE LOGITS
    guchi
    0.71
    gdx
    0.65
     co
    0.59
     Wilber
    0.57
     figure
    0.56
    overset
    0.56
     cal
    0.56
    La
    0.56
     la
    0.56
     La
    0.55
    Activations Density 0.071%

    No Known Activations