© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 25763
    Prev
    Next
    INDEX
    Explanations

    mathematical notations or logical constructs

    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
    InitStructure
    -0.60
    ımıza
    -0.59
     your
    -0.57
    路
    -0.57
     Duval
    -0.56
    なんでも
    -0.56
    ru
    -0.55
     pronta
    -0.55
     ready
    -0.54
     åt
    -0.54
    POSITIVE LOGITS
    –
    1.12
     myſelf
    1.06
     himſelf
    0.97
     fevere
    0.94
     Mino
    0.90
     ſtate
    0.89
    extAlignment
    0.87
    ✨:
    0.87
     ſever
    0.86
     numberWith
    0.85
    Activations Density 0.000%

    No Known Activations