© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14104
    Prev
    Next
    INDEX
    Explanations

    references to apples and oranges, typically in the context of food or treats

    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
    SBATCH
    -0.58
     kari
    -0.54
    uun
    -0.50
     Viernes
    -0.50
    tagext
    -0.50
    JSONException
    -0.49
    ércoles
    -0.47
    MIME
    -0.47
    xtype
    -0.46
     Koz
    -0.46
    POSITIVE LOGITS
     apples
    1.80
     Apples
    1.15
    Apples
    1.04
    apples
    1.02
    inas
    1.02
     inversely
    0.94
     apple
    0.91
     manzanas
    0.82
     متعلقه
    0.77
    inia
    0.77
    Activations Density 0.004%

    No Known Activations