© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14411
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of document or text snippet

    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
    WriteBarrier
    -0.89
    OGND
    -0.66
    FunctionFlags
    -0.62
    Abitanti
    -0.61
    يكب
    -0.60
    ValueGeneration
    -0.58
    XmlAccessorType
    -0.57
    esez
    -0.57
     EClass
    -0.57
    Джерела
    -0.57
    POSITIVE LOGITS
     Sob
    3.92
    Sob
    3.48
     sob
    2.84
     SOB
    1.88
    sob
    1.68
     sobriety
    1.24
     Sober
    1.23
     sobr
    0.96
     sobs
    0.90
     sober
    0.88
    Activations Density 0.001%

    No Known Activations