© 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. 1298
    Prev
    Next
    INDEX
    Explanations

    mentions of algorithms or computation

    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
     الدولى
    -0.89
    complexContent
    -0.84
    StructEnd
    -0.83
     utafitiHapana
    -0.78
    ρίου
    -0.76
     وتسجيلات
    -0.75
     Bastille
    -0.73
    ]")]
    -0.73
     Ephraim
    -0.71
    Hochspringen
    -0.71
    POSITIVE LOGITS
     AL
    1.57
     Al
    1.48
     Alg
    1.41
    Al
    1.34
    alg
    1.31
    Alg
    1.30
     alg
    1.27
     Alb
    1.21
     al
    1.20
     Alley
    1.20
    Activations Density 0.888%

    No Known Activations