© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2653
    Prev
    Next
    INDEX
    Explanations

    addition operations or incrementation

    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
    Negative Logits
    InputBorder
    -0.97
     houſe
    -0.93
    TypedDataSet
    -0.86
     myſelf
    -0.85
     pleaſure
    -0.81
     Chriftian
    -0.78
     Houſe
    -0.78
     whoſe
    -0.77
     ―――――
    -0.76
     ſche
    -0.75
    POSITIVE LOGITS
     +=
    3.03
    +=
    2.50
     -=
    2.33
     *=
    1.95
    +=(
    1.83
    ]+=
    1.77
     .=
    1.70
    +="
    1.57
    -=
    1.56
    *=
    1.51
    Activations Density 0.010%

    No Known Activations