© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15268
    Prev
    Next
    INDEX
    Explanations

    the specific mathematical or computational term "term" within technical contexts

    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
    parsedMessage
    -0.62
    marshaller
    -0.62
     يتيمه
    -0.61
    равда
    -0.60
    TestingModule
    -0.60
    TryGetValue
    -0.60
     EClass
    -0.59
     IndexPath
    -0.58
    ImageField
    -0.57
     ***!
    -0.57
    POSITIVE LOGITS
     myſelf
    0.68
     itſelf
    0.62
     ―――――
    0.57
     Monfieur
    0.57
    Clik
    0.56
    Demografie
    0.55
     Eſ
    0.54
    ":
    
    0.54
     Amu
    0.53
     Theſe
    0.52
    Activations Density 0.026%

    No Known Activations