© 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. 29845
    Prev
    Next
    INDEX
    Explanations

    terms related to poles and their properties in a mathematical context

    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
    __*/
    -0.75
    aronder
    -0.69
    anders
    -0.63
    ر
    -0.62
     Lowell
    -0.61
    Portail
    -0.60
     tess
    -0.59
    kosh
    -0.59
    PyExc
    -0.57
    бираем
    -0.57
    POSITIVE LOGITS
     pole
    1.29
    Pole
    1.28
     Pole
    1.26
    pole
    1.23
     poles
    1.22
     Poles
    1.10
    POLE
    1.08
    poles
    1.00
     dipole
    0.91
     Beller
    0.87
    Activations Density 0.004%

    No Known Activations