© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12825
    Prev
    Next
    INDEX
    Explanations

    references to specific data or datasets

    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
    MessageOf
    -0.92
     propOrder
    -0.87
     mergeFrom
    -0.85
    AndEndTag
    -0.82
    forRoot
    -0.80
     محفوظة
    -0.79
    expandindo
    -0.79
    oredCriteria
    -0.79
    Portail
    -0.75
    Bromoform
    -0.74
    POSITIVE LOGITS
     Dat
    3.02
    Dat
    2.53
    Datatype
    0.75
     datac
    0.72
     DAT
    0.71
    datac
    0.64
     datab
    0.64
    datab
    0.63
    bootstrapcdn
    0.54
    DAT
    0.52
    Activations Density 0.000%

    No Known Activations