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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15548
    Prev
    Next
    INDEX
    Explanations

    interconnected components in an engine's intake system

    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
     upstream
    -1.17
     Upstream
    -1.14
    upstream
    -1.07
    Upstream
    -0.97
     defaultstate
    -0.92
     tartalomajánló
    -0.91
     оригіналу
    -0.87
    ]--;
    -0.81
    GEBURTSDATUM
    -0.81
    LookAnd
    -0.75
    POSITIVE LOGITS
     downstream
    1.84
     posteriores
    0.74
     imedi
    0.55
     ExecuteAsync
    0.55
     inmediata
    0.53
     immediate
    0.50
    paddingVertical
    0.50
    glBind
    0.49
     Immediate
    0.48
     IMMEDIATE
    0.48
    Activations Density 0.001%

    No Known Activations