© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13614
    Prev
    Next
    INDEX
    Explanations

    references to connections or links

    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
     mas
    -0.55
    StoryboardSegue
    -0.52
     even
    -0.48
    Referencies
    -0.47
    ourse
    -0.47
    utilisons
    -0.47
    ecture
    -0.46
     advent
    -0.45
     Rin
    -0.45
    True
    -0.44
    POSITIVE LOGITS
     ejus
    0.79
    IsMutable
    0.74
     INTERESAR
    0.73
    Portail
    0.73
    Portale
    0.73
    AnchorStyles
    0.71
    InstanceState
    0.65
    uxxxx
    0.65
    azgo
    0.65
     <<<<<<<<<<<<<<
    0.64
    Activations Density 0.020%

    No Known Activations