© 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. 14052
    Prev
    Next
    INDEX
    Explanations

    key references or labels for different datasets and methods

    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
    didSet
    -0.74
    //-->
    -0.59
    initComponents
    -0.58
     Ukra
    -0.57
    DTM
    -0.56
     Anſ
    -0.53
     DTM
    -0.50
    :✨
    -0.50
     @"";
    -0.49
     Rishi
    -0.48
    POSITIVE LOGITS
    KA
    2.17
     KA
    1.54
    +#+#
    0.80
     initComponents
    0.78
    interopRequire
    0.72
    KURZBESCHREIBUNG
    0.71
     Infórmanos
    0.67
    KAT
    0.64
     @"/
    0.62
    tagHelperRunner
    0.59
    Activations Density 0.001%

    No Known Activations