© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1019
    Prev
    Next
    INDEX
    Explanations

    the presence or discussion of a fundamental or characteristic feature

    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
     property
    -0.68
    Demografie
    -0.66
     Property
    -0.62
     Rodrig
    -0.61
    indung
    -0.61
    Conseils
    -0.61
    EndInit
    -0.60
     Grundstück
    -0.60
    PropertyValue
    -0.59
    ContentAsync
    -0.58
    POSITIVE LOGITS
     feature
    4.47
     features
    4.28
    feature
    4.06
     Feature
    4.03
     Features
    4.00
    features
    3.89
    Feature
    3.86
    Features
    3.72
     FEATURE
    3.58
     FEATURES
    3.47
    Activations Density 0.182%

    No Known Activations