© 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. 3-RES-MATRYOSHKA-DC
    7. 1518
    Prev
    Next
    INDEX
    Explanations

    the word "feature" in different contexts

    oai_token-act-pair · gemini-2.0-flash
    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
    Alp
    -0.76
    indung
    -0.75
    Armand
    -0.70
     entanto
    -0.69
     neceff
    -0.69
     Talis
    -0.69
     Shand
    -0.68
     Pamph
    -0.68
     Vaj
    -0.68
     pessoais
    -0.67
    POSITIVE LOGITS
     features
    3.36
     feature
    3.23
     Features
    3.22
    features
    3.02
    Features
    2.98
     Feature
    2.97
    feature
    2.91
     FEATURES
    2.91
    Feature
    2.86
     FEATURE
    2.80
    Activations Density 0.075%

    No Known Activations