© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15907
    Prev
    Next
    INDEX
    Explanations

    references to scientific investigations or research activities

    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
    nsics
    -0.65
     investigator
    -0.64
     investigates
    -0.63
     Investigator
    -0.61
     INVESTIG
    -0.60
     investigating
    -0.58
     investig
    -0.57
    Investig
    -0.57
     investigated
    -0.57
     investigative
    -0.56
    POSITIVE LOGITS
     gawas
    0.68
    SBATCH
    0.68
    المناصب
    0.68
     المعيارى
    0.67
     saites
    0.67
     مشين
    0.66
    --
    0.65
    rrggbb
    0.64
    NUMX
    0.61
    Iden
    0.61
    Activations Density 0.057%

    No Known Activations