© 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. 2-RES-MATRYOSHKA-DC
    7. 4236
    Prev
    Next
    INDEX
    Explanations

    references to specific code constructs or programming language elements

    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
    NameInMap
    -0.92
     linkovi
    -0.75
    WithIOException
    -0.72
     Orr
    -0.68
     ostavi
    -0.66
     JSTOR
    -0.66
     endregion
    -0.66
    tvguidetime
    -0.65
    Demografía
    -0.65
    yntaxException
    -0.65
    POSITIVE LOGITS
    
    2.53
    
    0.51
    伏
    0.51
    睛
    0.50
     Ear
    0.49
     fins
    0.47
     jude
    0.47
    gü
    0.47
    caval
    0.47
     przew
    0.46
    Activations Density 0.000%

    No Known Activations