© 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. 14407
    Prev
    Next
    INDEX
    Explanations

    references to experimental effectiveness or outcomes of interventions

    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
     BoxDecoration
    -1.16
    Hentet
    -0.99
    
    -0.98
    期刊论文
    -0.93
    AutoresizingMask
    -0.90
     AssemblyVersion
    -0.89
     FetchType
    -0.87
    UnsafeEnabled
    -0.85
     NgModule
    -0.81
     <<<<<<<<<<<<<<
    -0.81
    POSITIVE LOGITS
    '
    0.57
    itemize
    0.50
     of
    0.49
     ''
    0.49
    ’
    0.48
     않
    0.47
    း
    0.47
     μας
    0.46
    ">(</
    0.45
    :"-"`
    0.45
    Activations Density 3.462%

    No Known Activations