© 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. 2-RES-MATRYOSHKA-DC
    7. 7455
    Prev
    Next
    INDEX
    Explanations

    code snippets related to database management and implementation

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.64
     cref
    -0.62
    ematic
    -0.62
    âteau
    -0.58
    pike
    -0.58
    دع
    -0.58
    ++++++++++++++++
    -0.57
    illingham
    -0.57
    CloseOperation
    -0.57
     Cabrio
    -0.57
    POSITIVE LOGITS
     Ind
    3.06
    Ind
    3.05
    IND
    2.94
     ind
    2.92
    ind
    2.91
     IND
    2.91
     Indi
    1.81
     indi
    1.80
    indi
    1.74
    inds
    1.61
    Activations Density 0.232%

    No Known Activations