© 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. 997
    Prev
    Next
    INDEX
    Explanations

    the concept of creating or stabilizing something

    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
    хи
    -0.58
    ど
    -0.56
    usercontent
    -0.55
     گیل
    -0.54
    wardship
    -0.54
     mocht
    -0.53
     itemView
    -0.52
    vitis
    -0.52
    lamine
    -0.51
    sendFile
    -0.51
    POSITIVE LOGITS
     formation
    2.56
     Formation
    2.36
    Formation
    2.25
     FORMATION
    2.25
     formations
    2.09
    formation
    1.98
     formed
    1.98
     Forming
    1.98
     Formed
    1.95
     forming
    1.92
    Activations Density 0.395%

    No Known Activations