© 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. 0-RES-MATRYOSHKA-DC
    7. 11041
    Prev
    Next
    INDEX
    Explanations

    references to the word "apex" in various capitalizations and forms

    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
     kasarigan
    -0.75
    ']?>
    -0.67
    WriteLiteral
    -0.65
     borealis
    -0.61
    naby
    -0.58
    mannian
    -0.57
     Kraw
    -0.57
    раздо
    -0.56
    ffindor
    -0.56
     dispoz
    -0.55
    POSITIVE LOGITS
     apex
    1.34
    apex
    1.24
     Apex
    0.96
    Apex
    0.79
     ali
    0.78
    ScopeManager
    0.75
    AnchorStyles
    0.71
    ьаж
    0.65
    TagHelper
    0.63
     bait
    0.62
    Activations Density 0.007%

    No Known Activations