© 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. 3-RES-MATRYOSHKA-DC
    7. 2819
    Prev
    Next
    INDEX
    Explanations

    fragments of code, configuration syntax, and logical conditions

    oai_token-act-pair · gemini-2.0-flash
    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
     zwy
    -0.63
    Dougall
    -0.62
     Anſ
    -0.62
     pleaſure
    -0.60
     typeName
    -0.58
     sagrada
    -0.58
     osteo
    -0.57
    limsy
    -0.57
     ſche
    -0.57
     Delano
    -0.57
    POSITIVE LOGITS
    writeFieldEnd
    0.73
    oredCriteria
    0.68
    +#+#
    0.65
    WriteAttribute
    0.64
    Condition
    0.63
    pexpr
    0.62
    addCriterion
    0.62
    CONDITION
    0.60
     cherchés
    0.59
     Condition
    0.57
    Activations Density 0.566%

    No Known Activations