© 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. 3520
    Prev
    Next
    INDEX
    Explanations

    references to numerical lists or grouped items

    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
    __":
    -0.62
    add
    -0.60
    AddRange
    -0.60
    migrationBuilder
    -0.58
     met
    -0.57
    BindView
    -0.56
     Add
    -0.54
    Add
    -0.54
    addCriterion
    -0.53
    ulemon
    -0.52
    POSITIVE LOGITS
     added
    2.14
     Added
    2.06
    added
    2.02
    Added
    1.91
     ADDED
    1.89
    ADDED
    1.30
     ajouté
    1.12
     añad
    1.12
     añadido
    1.08
     aggiunto
    0.94
    Activations Density 0.025%

    No Known Activations